Skip to content

GitLab

"vllm/vscode:/vscode.git/clone" did not exist on "23f3760217614807b1c1b08e593a54a824e42479"
Commit 99324e25 authored by zhuwenwen's avatar zhuwenwen
Browse files

Merge tag 'v0.9.2' into v0.9.2-ori

parents cc7f22a8 a5dd03c1
Hide whitespace changes
Inline Side-by-side
Showing with 1307 additions and 725 deletions
docs/models/hardware_supported_models/tpu.md 0 → 100644
View file @ 99324e25
---
title: TPU
---
[](){ #tpu-supported-models }
# TPU Supported Models
## Text-only Language Models
| Model | Architecture | Supported |
|-----------------------------------------------------|--------------------------------|-----------|
| mistralai/Mixtral-8x7B-Instruct-v0.1 | MixtralForCausalLM | 🟨 |
| mistralai/Mistral-Small-24B-Instruct-2501 | MistralForCausalLM | ✅ |
| mistralai/Codestral-22B-v0.1 | MistralForCausalLM | ✅ |
| mistralai/Mixtral-8x22B-Instruct-v0.1 | MixtralForCausalLM | ❌ |
| meta-llama/Llama-3.3-70B-Instruct | LlamaForCausalLM | ✅ |
| meta-llama/Llama-3.1-8B-Instruct | LlamaForCausalLM | ✅ |
| meta-llama/Llama-3.1-70B-Instruct | LlamaForCausalLM | ✅ |
| meta-llama/Llama-4-* | Llama4ForConditionalGeneration | ❌ |
| microsoft/Phi-3-mini-128k-instruct | Phi3ForCausalLM | 🟨 |
| microsoft/phi-4 | Phi3ForCausalLM | ❌ |
| google/gemma-3-27b-it | Gemma3ForConditionalGeneration | 🟨 |
| google/gemma-3-4b-it | Gemma3ForConditionalGeneration | ❌ |
| deepseek-ai/DeepSeek-R1 | DeepseekV3ForCausalLM | ❌ |
| deepseek-ai/DeepSeek-V3 | DeepseekV3ForCausalLM | ❌ |
| RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8 | LlamaForCausalLM | ✅ |
| RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 | LlamaForCausalLM | ✅ |
| Qwen/Qwen3-8B | Qwen3ForCausalLM | ✅ |
| Qwen/Qwen3-32B | Qwen3ForCausalLM | ✅ |
| Qwen/Qwen2.5-7B-Instruct | Qwen2ForCausalLM | ✅ |
| Qwen/Qwen2.5-32B | Qwen2ForCausalLM | ✅ |
| Qwen/Qwen2.5-14B-Instruct | Qwen2ForCausalLM | ✅ |
| Qwen/Qwen2.5-1.5B-Instruct | Qwen2ForCausalLM | 🟨 |
✅ Runs and optimized.
🟨 Runs and correct but not optimized to green yet.
❌ Does not pass accuracy test or does not run.
docs/models/pooling_models.md
View file @ 99324e25
......@@ -113,7 +113,7 @@ A code example can be found here: <gh-file:examples/offline_inference/basic/scor
## Online Serving
Our [OpenAI-Compatible Server][openai-compatible-server] provides endpoints that correspond to the offline APIs:
Our [OpenAI-Compatible Server][serving-openai-compatible-server] provides endpoints that correspond to the offline APIs:
- [Pooling API][pooling-api] is similar to `LLM.encode`, being applicable to all types of pooling models.
- [Embeddings API][embeddings-api] is similar to `LLM.embed`, accepting both text and [multi-modal inputs][multimodal-inputs] for embedding models.
......
docs/models/supported_models.md
View file @ 99324e25
......@@ -34,7 +34,7 @@ llm.apply_model(lambda model: print(type(model)))
If it is `TransformersForCausalLM` then it means it's based on Transformers!
!!! tip
You can force the use of `TransformersForCausalLM` by setting `model_impl="transformers"` for [offline-inference][offline-inference] or `--model-impl transformers` for the [openai-compatible-server][openai-compatible-server].
You can force the use of `TransformersForCausalLM` by setting `model_impl="transformers"` for [offline-inference][offline-inference] or `--model-impl transformers` for the [openai-compatible-server][serving-openai-compatible-server].
!!! note
vLLM may not fully optimise the Transformers implementation so you may see degraded performance if comparing a native model to a Transformers model in vLLM.
......@@ -53,8 +53,8 @@ For a model to be compatible with the Transformers backend for vLLM it must:
If the compatible model is:
- on the Hugging Face Model Hub, simply set `trust_remote_code=True` for [offline-inference][offline-inference] or `--trust-remote-code` for the [openai-compatible-server][openai-compatible-server].
- in a local directory, simply pass directory path to `model=<MODEL_DIR>` for [offline-inference][offline-inference] or `vllm serve <MODEL_DIR>` for the [openai-compatible-server][openai-compatible-server].
- on the Hugging Face Model Hub, simply set `trust_remote_code=True` for [offline-inference][offline-inference] or `--trust-remote-code` for the [openai-compatible-server][serving-openai-compatible-server].
- in a local directory, simply pass directory path to `model=<MODEL_DIR>` for [offline-inference][offline-inference] or `vllm serve <MODEL_DIR>` for the [openai-compatible-server][serving-openai-compatible-server].
This means that, with the Transformers backend for vLLM, new models can be used before they are officially supported in Transformers or vLLM!
......@@ -70,7 +70,10 @@ To make your model compatible with the Transformers backend, it needs:
2. `MyAttention` must use `ALL_ATTENTION_FUNCTIONS` to call attention.
3. `MyModel` must contain `_supports_attention_backend = True`.
```python title="modeling_my_model.py"
<details>
<summary>modeling_my_model.py</summary>
```python
from transformers import PreTrainedModel
from torch import nn
......@@ -93,6 +96,8 @@ class MyModel(PreTrainedModel):
_supports_attention_backend = True
```
</details>
Here is what happens in the background when this model is loaded:
1. The config is loaded.
......@@ -103,7 +108,10 @@ That's it!
For your model to be compatible with vLLM's tensor parallel and/or pipeline parallel features, you must add `base_model_tp_plan` and/or `base_model_pp_plan` to your model's config class:
```python title="configuration_my_model.py"
<details>
<summary>configuration_my_model.py</summary>
```python
from transformers import PretrainedConfig
......@@ -123,6 +131,8 @@ class MyConfig(PretrainedConfig):
}
```
</details>
- `base_model_tp_plan` is a `dict` that maps fully qualified layer name patterns to tensor parallel styles (currently only `"colwise"` and `"rowwise"` are supported).
- `base_model_pp_plan` is a `dict` that maps direct child layer names to `tuple`s of `list`s of `str`s:
* You only need to do this for layers which are not present on all pipeline stages
......@@ -168,7 +178,7 @@ Alternatively, you can [open an issue on GitHub](https://github.com/vllm-project
If you prefer, you can use the Hugging Face CLI to [download a model](https://huggingface.co/docs/huggingface_hub/guides/cli#huggingface-cli-download) or specific files from a model repository:
```console
```bash
# Download a model
huggingface-cli download HuggingFaceH4/zephyr-7b-beta
......@@ -183,7 +193,7 @@ huggingface-cli download HuggingFaceH4/zephyr-7b-beta eval_results.json
Use the Hugging Face CLI to [manage models](https://huggingface.co/docs/huggingface_hub/guides/manage-cache#scan-your-cache) stored in local cache:
```console
```bash
# List cached models
huggingface-cli scan-cache
......@@ -198,6 +208,9 @@ huggingface-cli scan-cache --dir ~/.cache/huggingface/hub
Use the Hugging Face CLI to interactively [delete downloaded model](https://huggingface.co/docs/huggingface_hub/guides/manage-cache#clean-your-cache) from the cache:
<details>
<summary>Commands</summary>
```console
# The `delete-cache` command requires extra dependencies to work with the TUI.
# Please run `pip install huggingface_hub[cli]` to install them.
......@@ -224,6 +237,8 @@ Start deletion.
Done. Deleted 1 repo(s) and 0 revision(s) for a total of 438.9M.
```
</details>
#### Using a proxy
Here are some tips for loading/downloading models from Hugging Face using a proxy:
......@@ -299,87 +314,97 @@ See [this page][generative-models] for more information on how to use generative
Specified using `--task generate`.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|---------------------------------------------------|-----------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|-----------------------------|
| `AquilaForCausalLM` | Aquila, Aquila2 | `BAAI/Aquila-7B`, `BAAI/AquilaChat-7B`, etc. | ✅︎ | ✅︎ |
| `ArcticForCausalLM` | Arctic | `Snowflake/snowflake-arctic-base`, `Snowflake/snowflake-arctic-instruct`, etc. | | ✅︎ |
| `BaiChuanForCausalLM` | Baichuan2, Baichuan | `baichuan-inc/Baichuan2-13B-Chat`, `baichuan-inc/Baichuan-7B`, etc. | ✅︎ | ✅︎ |
| `BambaForCausalLM` | Bamba | `ibm-ai-platform/Bamba-9B-fp8`, `ibm-ai-platform/Bamba-9B` | ✅︎ | ✅︎ |
| `BloomForCausalLM` | BLOOM, BLOOMZ, BLOOMChat | `bigscience/bloom`, `bigscience/bloomz`, etc. | | ✅︎ |
| `BartForConditionalGeneration` | BART | `facebook/bart-base`, `facebook/bart-large-cnn`, etc. | | |
| `ChatGLMModel`, `ChatGLMForConditionalGeneration` | ChatGLM | `THUDM/chatglm2-6b`, `THUDM/chatglm3-6b`, `ShieldLM-6B-chatglm3`, etc. | ✅︎ | ✅︎ |
| `CohereForCausalLM`, `Cohere2ForCausalLM` | Command-R | `CohereForAI/c4ai-command-r-v01`, `CohereForAI/c4ai-command-r7b-12-2024`, etc. | ✅︎ | ✅︎ |
| `DbrxForCausalLM` | DBRX | `databricks/dbrx-base`, `databricks/dbrx-instruct`, etc. | | ✅︎ |
| `DeciLMForCausalLM` | DeciLM | `nvidia/Llama-3_3-Nemotron-Super-49B-v1`, etc. | ✅︎ | ✅︎ |
| `DeepseekForCausalLM` | DeepSeek | `deepseek-ai/deepseek-llm-67b-base`, `deepseek-ai/deepseek-llm-7b-chat` etc. | | ✅︎ |
| `DeepseekV2ForCausalLM` | DeepSeek-V2 | `deepseek-ai/DeepSeek-V2`, `deepseek-ai/DeepSeek-V2-Chat` etc. | | ✅︎ |
| `DeepseekV3ForCausalLM` | DeepSeek-V3 | `deepseek-ai/DeepSeek-V3-Base`, `deepseek-ai/DeepSeek-V3` etc. | | ✅︎ |
| `ExaoneForCausalLM` | EXAONE-3 | `LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct`, etc. | ✅︎ | ✅︎ |
| `FalconForCausalLM` | Falcon | `tiiuae/falcon-7b`, `tiiuae/falcon-40b`, `tiiuae/falcon-rw-7b`, etc. | | ✅︎ |
| `FalconMambaForCausalLM` | FalconMamba | `tiiuae/falcon-mamba-7b`, `tiiuae/falcon-mamba-7b-instruct`, etc. | | ✅︎ |
| `FalconH1ForCausalLM` | Falcon-H1 | `tiiuae/Falcon-H1-34B-Base`, `tiiuae/Falcon-H1-34B-Instruct`, etc. | ✅︎ | ✅︎ |
| `GemmaForCausalLM` | Gemma | `google/gemma-2b`, `google/gemma-1.1-2b-it`, etc. | ✅︎ | ✅︎ |
| `Gemma2ForCausalLM` | Gemma 2 | `google/gemma-2-9b`, `google/gemma-2-27b`, etc. | ✅︎ | ✅︎ |
| `Gemma3ForCausalLM` | Gemma 3 | `google/gemma-3-1b-it`, etc. | ✅︎ | ✅︎ |
| `GlmForCausalLM` | GLM-4 | `THUDM/glm-4-9b-chat-hf`, etc. | ✅︎ | ✅︎ |
| `Glm4ForCausalLM` | GLM-4-0414 | `THUDM/GLM-4-32B-0414`, etc. | ✅︎ | ✅︎ |
| `GPT2LMHeadModel` | GPT-2 | `gpt2`, `gpt2-xl`, etc. | | ✅︎ |
| `GPTBigCodeForCausalLM` | StarCoder, SantaCoder, WizardCoder | `bigcode/starcoder`, `bigcode/gpt_bigcode-santacoder`, `WizardLM/WizardCoder-15B-V1.0`, etc. | ✅︎ | ✅︎ |
| `GPTJForCausalLM` | GPT-J | `EleutherAI/gpt-j-6b`, `nomic-ai/gpt4all-j`, etc. | | ✅︎ |
| `GPTNeoXForCausalLM` | GPT-NeoX, Pythia, OpenAssistant, Dolly V2, StableLM | `EleutherAI/gpt-neox-20b`, `EleutherAI/pythia-12b`, `OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5`, `databricks/dolly-v2-12b`, `stabilityai/stablelm-tuned-alpha-7b`, etc. | | ✅︎ |
| `GraniteForCausalLM` | Granite 3.0, Granite 3.1, PowerLM | `ibm-granite/granite-3.0-2b-base`, `ibm-granite/granite-3.1-8b-instruct`, `ibm/PowerLM-3b`, etc. | ✅︎ | ✅︎ |
| `GraniteMoeForCausalLM` | Granite 3.0 MoE, PowerMoE | `ibm-granite/granite-3.0-1b-a400m-base`, `ibm-granite/granite-3.0-3b-a800m-instruct`, `ibm/PowerMoE-3b`, etc. | ✅︎ | ✅︎ |
| `GraniteMoeHybridForCausalLM` | Granite 4.0 MoE Hybrid | `ibm-granite/granite-4.0-tiny-preview`, etc. | ✅︎ | ✅︎ |
| `GraniteMoeSharedForCausalLM` | Granite MoE Shared | `ibm-research/moe-7b-1b-active-shared-experts` (test model) | ✅︎ | ✅︎ |
| `GritLM` | GritLM | `parasail-ai/GritLM-7B-vllm`. | ✅︎ | ✅︎ |
| `Grok1ModelForCausalLM` | Grok1 | `hpcai-tech/grok-1`. | ✅︎ | ✅︎ |
| `InternLMForCausalLM` | InternLM | `internlm/internlm-7b`, `internlm/internlm-chat-7b`, etc. | ✅︎ | ✅︎ |
| `InternLM2ForCausalLM` | InternLM2 | `internlm/internlm2-7b`, `internlm/internlm2-chat-7b`, etc. | ✅︎ | ✅︎ |
| `InternLM3ForCausalLM` | InternLM3 | `internlm/internlm3-8b-instruct`, etc. | ✅︎ | ✅︎ |
| `JAISLMHeadModel` | Jais | `inceptionai/jais-13b`, `inceptionai/jais-13b-chat`, `inceptionai/jais-30b-v3`, `inceptionai/jais-30b-chat-v3`, etc. | | ✅︎ |
| `JambaForCausalLM` | Jamba | `ai21labs/AI21-Jamba-1.5-Large`, `ai21labs/AI21-Jamba-1.5-Mini`, `ai21labs/Jamba-v0.1`, etc. | ✅︎ | ✅︎ |
| `LlamaForCausalLM` | Llama 3.1, Llama 3, Llama 2, LLaMA, Yi | `meta-llama/Meta-Llama-3.1-405B-Instruct`, `meta-llama/Meta-Llama-3.1-70B`, `meta-llama/Meta-Llama-3-70B-Instruct`, `meta-llama/Llama-2-70b-hf`, `01-ai/Yi-34B`, etc. | ✅︎ | ✅︎ |
| `MambaForCausalLM` | Mamba | `state-spaces/mamba-130m-hf`, `state-spaces/mamba-790m-hf`, `state-spaces/mamba-2.8b-hf`, etc. | | ✅︎ |
| `MiniCPMForCausalLM` | MiniCPM | `openbmb/MiniCPM-2B-sft-bf16`, `openbmb/MiniCPM-2B-dpo-bf16`, `openbmb/MiniCPM-S-1B-sft`, etc. | ✅︎ | ✅︎ |
| `MiniCPM3ForCausalLM` | MiniCPM3 | `openbmb/MiniCPM3-4B`, etc. | ✅︎ | ✅︎ |
| `MistralForCausalLM` | Mistral, Mistral-Instruct | `mistralai/Mistral-7B-v0.1`, `mistralai/Mistral-7B-Instruct-v0.1`, etc. | ✅︎ | ✅︎ |
| `MixtralForCausalLM` | Mixtral-8x7B, Mixtral-8x7B-Instruct | `mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mistral-community/Mixtral-8x22B-v0.1`, etc. | ✅︎ | ✅︎ |
| `MPTForCausalLM` | MPT, MPT-Instruct, MPT-Chat, MPT-StoryWriter | `mosaicml/mpt-7b`, `mosaicml/mpt-7b-storywriter`, `mosaicml/mpt-30b`, etc. | | ✅︎ |
| `NemotronForCausalLM` | Nemotron-3, Nemotron-4, Minitron | `nvidia/Minitron-8B-Base`, `mgoin/Nemotron-4-340B-Base-hf-FP8`, etc. | ✅︎ | ✅︎ |
| `NemotronHForCausalLM` | Nemotron-H | `nvidia/Nemotron-H-8B-Base-8K`, `nvidia/Nemotron-H-47B-Base-8K`, `nvidia/Nemotron-H-56B-Base-8K`, etc. | ✅︎ | ✅︎ |
| `OLMoForCausalLM` | OLMo | `allenai/OLMo-1B-hf`, `allenai/OLMo-7B-hf`, etc. | | ✅︎ |
| `OLMo2ForCausalLM` | OLMo2 | `allenai/OLMo-2-0425-1B`, etc. | | ✅︎ |
| `OLMoEForCausalLM` | OLMoE | `allenai/OLMoE-1B-7B-0924`, `allenai/OLMoE-1B-7B-0924-Instruct`, etc. | | ✅︎ |
| `OPTForCausalLM` | OPT, OPT-IML | `facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc. | | ✅︎ |
| `OrionForCausalLM` | Orion | `OrionStarAI/Orion-14B-Base`, `OrionStarAI/Orion-14B-Chat`, etc. | | ✅︎ |
| `PhiForCausalLM` | Phi | `microsoft/phi-1_5`, `microsoft/phi-2`, etc. | ✅︎ | ✅︎ |
| `Phi3ForCausalLM` | Phi-4, Phi-3 | `microsoft/Phi-4-mini-instruct`, `microsoft/Phi-4`, `microsoft/Phi-3-mini-4k-instruct`, `microsoft/Phi-3-mini-128k-instruct`, `microsoft/Phi-3-medium-128k-instruct`, etc. | ✅︎ | ✅︎ |
| `Phi3SmallForCausalLM` | Phi-3-Small | `microsoft/Phi-3-small-8k-instruct`, `microsoft/Phi-3-small-128k-instruct`, etc. | | ✅︎ |
| `PhiMoEForCausalLM` | Phi-3.5-MoE | `microsoft/Phi-3.5-MoE-instruct`, etc. | ✅︎ | ✅︎ |
| `PersimmonForCausalLM` | Persimmon | `adept/persimmon-8b-base`, `adept/persimmon-8b-chat`, etc. | | ✅︎ |
| `Plamo2ForCausalLM` | PLaMo2 | `pfnet/plamo-2-1b`, `pfnet/plamo-2-8b`, etc. | | |
| `QWenLMHeadModel` | Qwen | `Qwen/Qwen-7B`, `Qwen/Qwen-7B-Chat`, etc. | ✅︎ | ✅︎ |
| `Qwen2ForCausalLM` | QwQ, Qwen2 | `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2-7B-Instruct`, `Qwen/Qwen2-7B`, etc. | ✅︎ | ✅︎ |
| `Qwen2MoeForCausalLM` | Qwen2MoE | `Qwen/Qwen1.5-MoE-A2.7B`, `Qwen/Qwen1.5-MoE-A2.7B-Chat`, etc. | | ✅︎ |
| `Qwen3ForCausalLM` | Qwen3 | `Qwen/Qwen3-8B`, etc. | ✅︎ | ✅︎ |
| `Qwen3MoeForCausalLM` | Qwen3MoE | `Qwen/Qwen3-30B-A3B`, etc. | | ✅︎ |
| `StableLmForCausalLM` | StableLM | `stabilityai/stablelm-3b-4e1t`, `stabilityai/stablelm-base-alpha-7b-v2`, etc. | | |
| `Starcoder2ForCausalLM` | Starcoder2 | `bigcode/starcoder2-3b`, `bigcode/starcoder2-7b`, `bigcode/starcoder2-15b`, etc. | | ✅︎ |
| `SolarForCausalLM` | Solar Pro | `upstage/solar-pro-preview-instruct`, etc. | ✅︎ | ✅︎ |
| `TeleChat2ForCausalLM` | TeleChat2 | `Tele-AI/TeleChat2-3B`, `Tele-AI/TeleChat2-7B`, `Tele-AI/TeleChat2-35B`, etc. | ✅︎ | ✅︎ |
| `TeleFLMForCausalLM` | TeleFLM | `CofeAI/FLM-2-52B-Instruct-2407`, `CofeAI/Tele-FLM`, etc. | ✅︎ | ✅︎ |
| `XverseForCausalLM` | XVERSE | `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc. | ✅︎ | ✅︎ |
| `MiniMaxText01ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-Text-01`, etc. | | |
| `Zamba2ForCausalLM` | Zamba2 | `Zyphra/Zamba2-7B-instruct`, `Zyphra/Zamba2-2.7B-instruct`, `Zyphra/Zamba2-1.2B-instruct`, etc. | | |
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|---------------------------------------------------|-----------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|-----------------------------|-----------------------|
| `AquilaForCausalLM` | Aquila, Aquila2 | `BAAI/Aquila-7B`, `BAAI/AquilaChat-7B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `ArcticForCausalLM` | Arctic | `Snowflake/snowflake-arctic-base`, `Snowflake/snowflake-arctic-instruct`, etc. | | ✅︎ | ✅︎ |
| `BaiChuanForCausalLM` | Baichuan2, Baichuan | `baichuan-inc/Baichuan2-13B-Chat`, `baichuan-inc/Baichuan-7B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `BambaForCausalLM` | Bamba | `ibm-ai-platform/Bamba-9B-fp8`, `ibm-ai-platform/Bamba-9B` | ✅︎ | ✅︎ | |
| `BloomForCausalLM` | BLOOM, BLOOMZ, BLOOMChat | `bigscience/bloom`, `bigscience/bloomz`, etc. | | ✅︎ | |
| `BartForConditionalGeneration` | BART | `facebook/bart-base`, `facebook/bart-large-cnn`, etc. | | | |
| `ChatGLMModel`, `ChatGLMForConditionalGeneration` | ChatGLM | `THUDM/chatglm2-6b`, `THUDM/chatglm3-6b`, `ShieldLM-6B-chatglm3`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `CohereForCausalLM`, `Cohere2ForCausalLM` | Command-R | `CohereForAI/c4ai-command-r-v01`, `CohereForAI/c4ai-command-r7b-12-2024`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `DbrxForCausalLM` | DBRX | `databricks/dbrx-base`, `databricks/dbrx-instruct`, etc. | | ✅︎ | ✅︎ |
| `DeciLMForCausalLM` | DeciLM | `nvidia/Llama-3_3-Nemotron-Super-49B-v1`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `DeepseekForCausalLM` | DeepSeek | `deepseek-ai/deepseek-llm-67b-base`, `deepseek-ai/deepseek-llm-7b-chat` etc. | | ✅︎ | ✅︎ |
| `DeepseekV2ForCausalLM` | DeepSeek-V2 | `deepseek-ai/DeepSeek-V2`, `deepseek-ai/DeepSeek-V2-Chat` etc. | | ✅︎ | ✅︎ |
| `DeepseekV3ForCausalLM` | DeepSeek-V3 | `deepseek-ai/DeepSeek-V3-Base`, `deepseek-ai/DeepSeek-V3` etc. | | ✅︎ | ✅︎ |
| `Dots1ForCausalLM` | dots.llm1 | `rednote-hilab/dots.llm1.base`, `rednote-hilab/dots.llm1.inst` etc. | | ✅︎ | ✅︎ |
| `Ernie4_5_ForCausalLM` | Ernie4.5 | `baidu/ERNIE-4.5-0.3B-PT`,etc. | | ✅︎ | ✅︎ |
| `Ernie4_5_MoeForCausalLM` | Ernie4.5MoE | `baidu/ERNIE-4.5-21B-A3B-PT`, `baidu/ERNIE-4.5-300B-A47B-PT`, etc. | | ✅︎ | ✅︎ |
| `ExaoneForCausalLM` | EXAONE-3 | `LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `FalconForCausalLM` | Falcon | `tiiuae/falcon-7b`, `tiiuae/falcon-40b`, `tiiuae/falcon-rw-7b`, etc. | | ✅︎ | ✅︎ |
| `FalconMambaForCausalLM` | FalconMamba | `tiiuae/falcon-mamba-7b`, `tiiuae/falcon-mamba-7b-instruct`, etc. | | ✅︎ | ✅︎ |
| `FalconH1ForCausalLM` | Falcon-H1 | `tiiuae/Falcon-H1-34B-Base`, `tiiuae/Falcon-H1-34B-Instruct`, etc. | ✅︎ | ✅︎ | |
| `GemmaForCausalLM` | Gemma | `google/gemma-2b`, `google/gemma-1.1-2b-it`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Gemma2ForCausalLM` | Gemma 2 | `google/gemma-2-9b`, `google/gemma-2-27b`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Gemma3ForCausalLM` | Gemma 3 | `google/gemma-3-1b-it`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Gemma3nForConditionalGeneration` | Gemma 3n | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
| `GlmForCausalLM` | GLM-4 | `THUDM/glm-4-9b-chat-hf`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Glm4ForCausalLM` | GLM-4-0414 | `THUDM/GLM-4-32B-0414`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GPT2LMHeadModel` | GPT-2 | `gpt2`, `gpt2-xl`, etc. | | ✅︎ | ✅︎ |
| `GPTBigCodeForCausalLM` | StarCoder, SantaCoder, WizardCoder | `bigcode/starcoder`, `bigcode/gpt_bigcode-santacoder`, `WizardLM/WizardCoder-15B-V1.0`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GPTJForCausalLM` | GPT-J | `EleutherAI/gpt-j-6b`, `nomic-ai/gpt4all-j`, etc. | | ✅︎ | ✅︎ |
| `GPTNeoXForCausalLM` | GPT-NeoX, Pythia, OpenAssistant, Dolly V2, StableLM | `EleutherAI/gpt-neox-20b`, `EleutherAI/pythia-12b`, `OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5`, `databricks/dolly-v2-12b`, `stabilityai/stablelm-tuned-alpha-7b`, etc. | | ✅︎ | ✅︎ |
| `GraniteForCausalLM` | Granite 3.0, Granite 3.1, PowerLM | `ibm-granite/granite-3.0-2b-base`, `ibm-granite/granite-3.1-8b-instruct`, `ibm/PowerLM-3b`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GraniteMoeForCausalLM` | Granite 3.0 MoE, PowerMoE | `ibm-granite/granite-3.0-1b-a400m-base`, `ibm-granite/granite-3.0-3b-a800m-instruct`, `ibm/PowerMoE-3b`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GraniteMoeHybridForCausalLM` | Granite 4.0 MoE Hybrid | `ibm-granite/granite-4.0-tiny-preview`, etc. | ✅︎ | ✅︎ | |
| `GraniteMoeSharedForCausalLM` | Granite MoE Shared | `ibm-research/moe-7b-1b-active-shared-experts` (test model) | ✅︎ | ✅︎ | ✅︎ |
| `GritLM` | GritLM | `parasail-ai/GritLM-7B-vllm`. | ✅︎ | ✅︎ | |
| `Grok1ModelForCausalLM` | Grok1 | `hpcai-tech/grok-1`. | ✅︎ | ✅︎ | ✅︎ |
| `HunYuanMoEV1ForCausalLM` | Hunyuan-80B-A13B | `tencent/Hunyuan-A13B-Instruct`, `tencent/Hunyuan-A13B-Pretrain`, `tencent/Hunyuan-A13B-Instruct-FP8`etc. | | | ✅︎ |
| `InternLMForCausalLM` | InternLM | `internlm/internlm-7b`, `internlm/internlm-chat-7b`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `InternLM2ForCausalLM` | InternLM2 | `internlm/internlm2-7b`, `internlm/internlm2-chat-7b`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `InternLM3ForCausalLM` | InternLM3 | `internlm/internlm3-8b-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `JAISLMHeadModel` | Jais | `inceptionai/jais-13b`, `inceptionai/jais-13b-chat`, `inceptionai/jais-30b-v3`, `inceptionai/jais-30b-chat-v3`, etc. | | ✅︎ | ✅︎ |
| `JambaForCausalLM` | Jamba | `ai21labs/AI21-Jamba-1.5-Large`, `ai21labs/AI21-Jamba-1.5-Mini`, `ai21labs/Jamba-v0.1`, etc. | ✅︎ | ✅︎ | |
| `LlamaForCausalLM` | Llama 3.1, Llama 3, Llama 2, LLaMA, Yi | `meta-llama/Meta-Llama-3.1-405B-Instruct`, `meta-llama/Meta-Llama-3.1-70B`, `meta-llama/Meta-Llama-3-70B-Instruct`, `meta-llama/Llama-2-70b-hf`, `01-ai/Yi-34B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MambaForCausalLM` | Mamba | `state-spaces/mamba-130m-hf`, `state-spaces/mamba-790m-hf`, `state-spaces/mamba-2.8b-hf`, etc. | | ✅︎ | |
| `Mamba2ForCausalLM` | Mamba2 | `mistralai/Mamba-Codestral-7B-v0.1`, etc. | | ✅︎ | |
| `MiniCPMForCausalLM` | MiniCPM | `openbmb/MiniCPM-2B-sft-bf16`, `openbmb/MiniCPM-2B-dpo-bf16`, `openbmb/MiniCPM-S-1B-sft`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MiniCPM3ForCausalLM` | MiniCPM3 | `openbmb/MiniCPM3-4B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MistralForCausalLM` | Mistral, Mistral-Instruct | `mistralai/Mistral-7B-v0.1`, `mistralai/Mistral-7B-Instruct-v0.1`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MixtralForCausalLM` | Mixtral-8x7B, Mixtral-8x7B-Instruct | `mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mistral-community/Mixtral-8x22B-v0.1`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MPTForCausalLM` | MPT, MPT-Instruct, MPT-Chat, MPT-StoryWriter | `mosaicml/mpt-7b`, `mosaicml/mpt-7b-storywriter`, `mosaicml/mpt-30b`, etc. | | ✅︎ | ✅︎ |
| `NemotronForCausalLM` | Nemotron-3, Nemotron-4, Minitron | `nvidia/Minitron-8B-Base`, `mgoin/Nemotron-4-340B-Base-hf-FP8`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `NemotronHForCausalLM` | Nemotron-H | `nvidia/Nemotron-H-8B-Base-8K`, `nvidia/Nemotron-H-47B-Base-8K`, `nvidia/Nemotron-H-56B-Base-8K`, etc. | ✅︎ | ✅︎ | |
| `OLMoForCausalLM` | OLMo | `allenai/OLMo-1B-hf`, `allenai/OLMo-7B-hf`, etc. | | ✅︎ | ✅︎ |
| `OLMo2ForCausalLM` | OLMo2 | `allenai/OLMo-2-0425-1B`, etc. | | ✅︎ | ✅︎ |
| `OLMoEForCausalLM` | OLMoE | `allenai/OLMoE-1B-7B-0924`, `allenai/OLMoE-1B-7B-0924-Instruct`, etc. | | ✅︎ | ✅︎ |
| `OPTForCausalLM` | OPT, OPT-IML | `facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc. | | ✅︎ | ✅︎ |
| `OrionForCausalLM` | Orion | `OrionStarAI/Orion-14B-Base`, `OrionStarAI/Orion-14B-Chat`, etc. | | ✅︎ | ✅︎ |
| `PhiForCausalLM` | Phi | `microsoft/phi-1_5`, `microsoft/phi-2`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Phi3ForCausalLM` | Phi-4, Phi-3 | `microsoft/Phi-4-mini-instruct`, `microsoft/Phi-4`, `microsoft/Phi-3-mini-4k-instruct`, `microsoft/Phi-3-mini-128k-instruct`, `microsoft/Phi-3-medium-128k-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Phi3SmallForCausalLM` | Phi-3-Small | `microsoft/Phi-3-small-8k-instruct`, `microsoft/Phi-3-small-128k-instruct`, etc. | | ✅︎ | ✅︎ |
| `PhiMoEForCausalLM` | Phi-3.5-MoE | `microsoft/Phi-3.5-MoE-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `PersimmonForCausalLM` | Persimmon | `adept/persimmon-8b-base`, `adept/persimmon-8b-chat`, etc. | | ✅︎ | ✅︎ |
| `Plamo2ForCausalLM` | PLaMo2 | `pfnet/plamo-2-1b`, `pfnet/plamo-2-8b`, etc. | | | |
| `QWenLMHeadModel` | Qwen | `Qwen/Qwen-7B`, `Qwen/Qwen-7B-Chat`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2ForCausalLM` | QwQ, Qwen2 | `Qwen/QwQ-32B-Preview`, `Qwen/Qwen2-7B-Instruct`, `Qwen/Qwen2-7B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2MoeForCausalLM` | Qwen2MoE | `Qwen/Qwen1.5-MoE-A2.7B`, `Qwen/Qwen1.5-MoE-A2.7B-Chat`, etc. | | ✅︎ | ✅︎ |
| `Qwen3ForCausalLM` | Qwen3 | `Qwen/Qwen3-8B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen3MoeForCausalLM` | Qwen3MoE | `Qwen/Qwen3-30B-A3B`, etc. | | ✅︎ | ✅︎ |
| `StableLmForCausalLM` | StableLM | `stabilityai/stablelm-3b-4e1t`, `stabilityai/stablelm-base-alpha-7b-v2`, etc. | | | ✅︎ |
| `Starcoder2ForCausalLM` | Starcoder2 | `bigcode/starcoder2-3b`, `bigcode/starcoder2-7b`, `bigcode/starcoder2-15b`, etc. | | ✅︎ | ✅︎ |
| `SolarForCausalLM` | Solar Pro | `upstage/solar-pro-preview-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `TeleChat2ForCausalLM` | TeleChat2 | `Tele-AI/TeleChat2-3B`, `Tele-AI/TeleChat2-7B`, `Tele-AI/TeleChat2-35B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `TeleFLMForCausalLM` | TeleFLM | `CofeAI/FLM-2-52B-Instruct-2407`, `CofeAI/Tele-FLM`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `XverseForCausalLM` | XVERSE | `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MiniMaxM1ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-M1-40k`, `MiniMaxAI/MiniMax-M1-80k`etc. | | | |
| `MiniMaxText01ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-Text-01`, etc. | | | |
| `Zamba2ForCausalLM` | Zamba2 | `Zyphra/Zamba2-7B-instruct`, `Zyphra/Zamba2-2.7B-instruct`, `Zyphra/Zamba2-1.2B-instruct`, etc. | | | |
!!! note
Currently, the ROCm version of vLLM supports Mistral and Mixtral only for context lengths up to 4096.
!!! note
Only text inputs are currently supported for `Gemma3nForConditionalGeneration`. To use this model, please upgrade Hugging Face Transformers to version 4.53.0.
### Pooling Models
See [this page](./pooling_models.md) for more information on how to use pooling models.
!!! warning
!!! important
Since some model architectures support both generative and pooling tasks,
you should explicitly specify the task type to ensure that the model is used in pooling mode instead of generative mode.
......@@ -387,18 +412,19 @@ See [this page](./pooling_models.md) for more information on how to use pooling
Specified using `--task embed`.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|--------------------------------------------------------|---------------------|---------------------------------------------------------------------------------------------------------------------|------------------------|-----------------------------|
| `BertModel` | BERT-based | `BAAI/bge-base-en-v1.5`, `Snowflake/snowflake-arctic-embed-xs`, etc. | | |
| `Gemma2Model` | Gemma 2-based | `BAAI/bge-multilingual-gemma2`, etc. | ✅︎ | |
| `GritLM` | GritLM | `parasail-ai/GritLM-7B-vllm`. | ✅︎ | ✅︎ |
| `GteModel` | Arctic-Embed-2.0-M | `Snowflake/snowflake-arctic-embed-m-v2.0`. | ︎ | |
| `GteNewModel` | mGTE-TRM (see note) | `Alibaba-NLP/gte-multilingual-base`, etc. | ︎ | ︎ |
| `ModernBertModel` | ModernBERT-based | `Alibaba-NLP/gte-modernbert-base`, etc. | ︎ | ︎ |
| `NomicBertModel` | Nomic BERT | `nomic-ai/nomic-embed-text-v1`, `nomic-ai/nomic-embed-text-v2-moe`, `Snowflake/snowflake-arctic-embed-m-long`, etc. | ︎ | ︎ |
| `LlamaModel`, `LlamaForCausalLM`, `MistralModel`, etc. | Llama-based | `intfloat/e5-mistral-7b-instruct`, etc. | ✅︎ | ✅︎ |
| `Qwen2Model`, `Qwen2ForCausalLM` | Qwen2-based | `ssmits/Qwen2-7B-Instruct-embed-base` (see note), `Alibaba-NLP/gte-Qwen2-7B-instruct` (see note), etc. | ✅︎ | ✅︎ |
| `RobertaModel`, `RobertaForMaskedLM` | RoBERTa-based | `sentence-transformers/all-roberta-large-v1`, etc. | | |
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|--------------------------------------------------------|---------------------|---------------------------------------------------------------------------------------------------------------------|----------------------|---------------------------|-----------------------|
| `BertModel` | BERT-based | `BAAI/bge-base-en-v1.5`, `Snowflake/snowflake-arctic-embed-xs`, etc. | | | |
| `Gemma2Model` | Gemma 2-based | `BAAI/bge-multilingual-gemma2`, etc. | ✅︎ | | ✅︎ |
| `GritLM` | GritLM | `parasail-ai/GritLM-7B-vllm`. | ✅︎ | ✅︎ | |
| `GteModel` | Arctic-Embed-2.0-M | `Snowflake/snowflake-arctic-embed-m-v2.0`. | ︎ | | |
| `GteNewModel` | mGTE-TRM (see note) | `Alibaba-NLP/gte-multilingual-base`, etc. | ︎ | ︎ | |
| `ModernBertModel` | ModernBERT-based | `Alibaba-NLP/gte-modernbert-base`, etc. | ︎ | ︎ | |
| `NomicBertModel` | Nomic BERT | `nomic-ai/nomic-embed-text-v1`, `nomic-ai/nomic-embed-text-v2-moe`, `Snowflake/snowflake-arctic-embed-m-long`, etc. | ︎ | ︎ | |
| `LlamaModel`, `LlamaForCausalLM`, `MistralModel`, etc. | Llama-based | `intfloat/e5-mistral-7b-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2Model`, `Qwen2ForCausalLM` | Qwen2-based | `ssmits/Qwen2-7B-Instruct-embed-base` (see note), `Alibaba-NLP/gte-Qwen2-7B-instruct` (see note), etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen3Model`, `Qwen3ForCausalLM` | Qwen3-based | `Qwen/Qwen3-Embedding-0.6B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `RobertaModel`, `RobertaForMaskedLM` | RoBERTa-based | `sentence-transformers/all-roberta-large-v1`, etc. | | | |
!!! note
`ssmits/Qwen2-7B-Instruct-embed-base` has an improperly defined Sentence Transformers config.
......@@ -409,7 +435,7 @@ Specified using `--task embed`.
See [relevant issue on HF Transformers](https://github.com/huggingface/transformers/issues/34882).
!!! note
`jinaai/jina-embeddings-v3` supports multiple tasks through lora, while vllm temporarily only supports text-matching tasks by merging lora weights.
`jinaai/jina-embeddings-v3` supports multiple tasks through LoRA, while vllm temporarily only supports text-matching tasks by merging LoRA weights.
!!! note
The second-generation GTE model (mGTE-TRM) is named `NewModel`. The name `NewModel` is too generic, you should set `--hf-overrides '{"architectures": ["GteNewModel"]}'` to specify the use of the `GteNewModel` architecture.
......@@ -422,16 +448,17 @@ of the whole prompt are extracted from the normalized hidden state corresponding
Specified using `--task reward`.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|---------------------------|-----------------|------------------------------------------------------------------------|------------------------|-----------------------------|
| `InternLM2ForRewardModel` | InternLM2-based | `internlm/internlm2-1_8b-reward`, `internlm/internlm2-7b-reward`, etc. | ✅︎ | ✅︎ |
| `LlamaForCausalLM` | Llama-based | `peiyi9979/math-shepherd-mistral-7b-prm`, etc. | ✅︎ | ✅︎ |
| `Qwen2ForRewardModel` | Qwen2-based | `Qwen/Qwen2.5-Math-RM-72B`, etc. | ✅︎ | ✅︎ |
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|---------------------------|-----------------|------------------------------------------------------------------------|------------------------|-----------------------------|-----------------------|
| `InternLM2ForRewardModel` | InternLM2-based | `internlm/internlm2-1_8b-reward`, `internlm/internlm2-7b-reward`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `LlamaForCausalLM` | Llama-based | `peiyi9979/math-shepherd-mistral-7b-prm`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2ForRewardModel` | Qwen2-based | `Qwen/Qwen2.5-Math-RM-72B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2ForProcessRewardModel` | Qwen2-based | `Qwen/Qwen2.5-Math-PRM-7B`, etc. | ✅︎ | ✅︎ | ✅︎ |
If your model is not in the above list, we will try to automatically convert the model using
[as_reward_model][vllm.model_executor.models.adapters.as_reward_model]. By default, we return the hidden states of each token directly.
!!! warning
!!! important
For process-supervised reward models such as `peiyi9979/math-shepherd-mistral-7b-prm`, the pooling config should be set explicitly,
e.g.: `--override-pooler-config '{"pooling_type": "STEP", "step_tag_id": 123, "returned_token_ids": [456, 789]}'`.
......@@ -439,22 +466,39 @@ If your model is not in the above list, we will try to automatically convert the
Specified using `--task classify`.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|----------------------------------|----------|----------------------------------------|------------------------|-----------------------------|
| `JambaForSequenceClassification` | Jamba | `ai21labs/Jamba-tiny-reward-dev`, etc. | ✅︎ | ✅︎ |
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|----------------------------------|----------|----------------------------------------|------------------------|-----------------------------|-----------------------|
| `JambaForSequenceClassification` | Jamba | `ai21labs/Jamba-tiny-reward-dev`, etc. | ✅︎ | ✅︎ | |
| `GPT2ForSequenceClassification` | GPT2 | `nie3e/sentiment-polish-gpt2-small` | | | ✅︎ |
If your model is not in the above list, we will try to automatically convert the model using
[as_classification_model][vllm.model_executor.models.adapters.as_classification_model]. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
[as_seq_cls_model][vllm.model_executor.models.adapters.as_seq_cls_model]. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
#### Sentence Pair Scoring
Specified using `--task score`.
| Architecture | Models | Example HF Models |
|---------------------------------------|-------------------|----------------------------------------------|
| `BertForSequenceClassification` | BERT-based | `cross-encoder/ms-marco-MiniLM-L-6-v2`, etc. |
| `RobertaForSequenceClassification` | RoBERTa-based | `cross-encoder/quora-roberta-base`, etc. |
| `XLMRobertaForSequenceClassification` | XLM-RoBERTa-based | `BAAI/bge-reranker-v2-m3`, etc. |
| Architecture | Models | Example HF Models | [V1](gh-issue:8779) |
|---------------------------------------|-------------------|--------------------------------------------------------------------------------------|---------------------|
| `BertForSequenceClassification` | BERT-based | `cross-encoder/ms-marco-MiniLM-L-6-v2`, etc. | |
| `Qwen2ForSequenceClassification` | Qwen2-based | `mixedbread-ai/mxbai-rerank-base-v2` (see note), etc. | ✅︎ |
| `Qwen3ForSequenceClassification` | Qwen3-based | `tomaarsen/Qwen3-Reranker-0.6B-seq-cls`, `Qwen/Qwen3-Reranker-0.6B` (see note), etc. | ✅︎ |
| `RobertaForSequenceClassification` | RoBERTa-based | `cross-encoder/quora-roberta-base`, etc. | |
| `XLMRobertaForSequenceClassification` | XLM-RoBERTa-based | `BAAI/bge-reranker-v2-m3`, etc. | |
!!! note
Load the official original `mxbai-rerank-v2` by using the following command.
```bash
vllm serve mixedbread-ai/mxbai-rerank-base-v2 --hf_overrides '{"architectures": ["Qwen2ForSequenceClassification"],"classifier_from_token": ["0", "1"], "method": "from_2_way_softmax"}'
```
!!! note
Load the official original `Qwen3 Reranker` by using the following command. More information can be found at: <gh-file:examples/offline_inference/qwen3_reranker.py>.
```bash
vllm serve Qwen/Qwen3-Reranker-0.6B --hf_overrides '{"architectures": ["Qwen3ForSequenceClassification"],"classifier_from_token": ["no", "yes"],"is_original_qwen3_reranker": true}'
```
[](){ #supported-mm-models }
......@@ -477,7 +521,7 @@ On the other hand, modalities separated by `/` are mutually exclusive.
See [this page][multimodal-inputs] on how to pass multi-modal inputs to the model.
!!! warning
!!! important
**To enable multiple multi-modal items per text prompt in vLLM V0**, you have to set `limit_mm_per_prompt` (offline inference)
or `--limit-mm-per-prompt` (online serving). For example, to enable passing up to 4 images per text prompt:
......@@ -513,45 +557,48 @@ Specified using `--task generate`.
| Architecture | Models | Inputs | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|----------------------------------------------|--------------------------------------------------------------------------|-----------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|-----------------------------|-----------------------|
| `AriaForConditionalGeneration` | Aria | T + I<sup>+</sup> | `rhymes-ai/Aria` | | | ✅︎ |
| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereForAI/aya-vision-8b`, `CohereForAI/aya-vision-32b`, etc. | | ✅︎ | ✅︎ |
| `Blip2ForConditionalGeneration` | BLIP-2 | T + I<sup>E</sup> | `Salesforce/blip2-opt-2.7b`, `Salesforce/blip2-opt-6.7b`, etc. | | ✅︎ | ✅︎ |
| `ChameleonForConditionalGeneration` | Chameleon | T + I | `facebook/chameleon-7b` etc. | | ✅︎ | ✅︎ |
| `DeepseekVLV2ForCausalLM`<sup>^</sup> | DeepSeek-VL2 | T + I<sup>+</sup> | `deepseek-ai/deepseek-vl2-tiny`, `deepseek-ai/deepseek-vl2-small`, `deepseek-ai/deepseek-vl2` etc. | | ✅︎ | ✅︎ |
| `AriaForConditionalGeneration` | Aria | T + I<sup>+</sup> | `rhymes-ai/Aria` | | | ✅︎ |
| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereForAI/aya-vision-8b`, `CohereForAI/aya-vision-32b`, etc. | | ✅︎ | ✅︎ |
| `Blip2ForConditionalGeneration` | BLIP-2 | T + I<sup>E</sup> | `Salesforce/blip2-opt-2.7b`, `Salesforce/blip2-opt-6.7b`, etc. | | ✅︎ | ✅︎ |
| `ChameleonForConditionalGeneration` | Chameleon | T + I | `facebook/chameleon-7b` etc. | | ✅︎ | ✅︎ |
| `DeepseekVLV2ForCausalLM`<sup>^</sup> | DeepSeek-VL2 | T + I<sup>+</sup> | `deepseek-ai/deepseek-vl2-tiny`, `deepseek-ai/deepseek-vl2-small`, `deepseek-ai/deepseek-vl2` etc. | | ✅︎ | ✅︎ |
| `Florence2ForConditionalGeneration` | Florence-2 | T + I | `microsoft/Florence-2-base`, `microsoft/Florence-2-large` etc. | | | |
| `FuyuForCausalLM` | Fuyu | T + I | `adept/fuyu-8b` etc. | | ✅︎ | ✅︎ |
| `FuyuForCausalLM` | Fuyu | T + I | `adept/fuyu-8b` etc. | | ✅︎ | ✅︎ |
| `Gemma3ForConditionalGeneration` | Gemma 3 | T + I<sup>+</sup> | `google/gemma-3-4b-it`, `google/gemma-3-27b-it`, etc. | ✅︎ | ✅︎ | ⚠️ |
| `GLM4VForCausalLM`<sup>^</sup> | GLM-4V | T + I | `THUDM/glm-4v-9b`, `THUDM/cogagent-9b-20241220` etc. | ✅︎ | ✅︎ | ✅︎ |
| `Glm4vForConditionalGeneration` | GLM-4.1V-Thinking | T + I<sup>E+</sup> + V<sup>E+</sup> | `THUDM/GLM-4.1V-9B-Thinkg`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GraniteSpeechForConditionalGeneration` | Granite Speech | T + A | `ibm-granite/granite-speech-3.3-8b` | ✅︎ | ✅︎ | ✅︎ |
| `H2OVLChatModel` | H2OVL | T + I<sup>E+</sup> | `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc. | | ✅︎ | ✅︎\* |
| `Idefics3ForConditionalGeneration` | Idefics3 | T + I | `HuggingFaceM4/Idefics3-8B-Llama3` etc. | ✅︎ | | ✅︎ |
| `InternVLChatModel` | InternVL 3.0, InternVideo 2.5, InternVL 2.5, Mono-InternVL, InternVL 2.0 | T + I<sup>E+</sup> + (V<sup>E+</sup>) | `OpenGVLab/InternVL3-9B`, `OpenGVLab/InternVideo2_5_Chat_8B`, `OpenGVLab/InternVL2_5-4B`, `OpenGVLab/Mono-InternVL-2B`, `OpenGVLab/InternVL2-4B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `KimiVLForConditionalGeneration` | Kimi-VL-A3B-Instruct, Kimi-VL-A3B-Thinking | T + I<sup>+</sup> | `moonshotai/Kimi-VL-A3B-Instruct`, `moonshotai/Kimi-VL-A3B-Thinking` | | | ✅︎ |
| `Llama4ForConditionalGeneration` | Llama 4 | T + I<sup>+</sup> | `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct`, etc. | | ✅︎ | ✅︎ |
| `LlavaForConditionalGeneration` | LLaVA-1.5 | T + I<sup>E+</sup> | `llava-hf/llava-1.5-7b-hf`, `TIGER-Lab/Mantis-8B-siglip-llama3` (see note), etc. | | ✅︎ | ✅︎ |
| `LlavaNextForConditionalGeneration` | LLaVA-NeXT | T + I<sup>E+</sup> | `llava-hf/llava-v1.6-mistral-7b-hf`, `llava-hf/llava-v1.6-vicuna-7b-hf`, etc. | | ✅︎ | ✅︎ |
| `LlavaNextVideoForConditionalGeneration` | LLaVA-NeXT-Video | T + V | `llava-hf/LLaVA-NeXT-Video-7B-hf`, etc. | | ✅︎ | ✅︎ |
| `LlavaOnevisionForConditionalGeneration` | LLaVA-Onevision | T + I<sup>+</sup> + V<sup>+</sup> | `llava-hf/llava-onevision-qwen2-7b-ov-hf`, `llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc. | | ✅︎ | ✅︎ |
| `H2OVLChatModel` | H2OVL | T + I<sup>E+</sup> | `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc. | | ✅︎ | ✅︎\* |
| `Idefics3ForConditionalGeneration` | Idefics3 | T + I | `HuggingFaceM4/Idefics3-8B-Llama3` etc. | ✅︎ | | ✅︎ |
| `InternVLChatModel` | InternVL 3.0, InternVideo 2.5, InternVL 2.5, Mono-InternVL, InternVL 2.0 | T + I<sup>E+</sup> + (V<sup>E+</sup>) | `OpenGVLab/InternVL3-9B`, `OpenGVLab/InternVideo2_5_Chat_8B`, `OpenGVLab/InternVL2_5-4B`, `OpenGVLab/Mono-InternVL-2B`, `OpenGVLab/InternVL2-4B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `KeyeForConditionalGeneration` | Keye-VL-8B-Preview | T + I<sup>E+</sup> + V<sup>E+</sup> | `Kwai-Keye/Keye-VL-8B-Preview` | | | ✅︎ |
| `KimiVLForConditionalGeneration` | Kimi-VL-A3B-Instruct, Kimi-VL-A3B-Thinking | T + I<sup>+</sup> | `moonshotai/Kimi-VL-A3B-Instruct`, `moonshotai/Kimi-VL-A3B-Thinking` | | | ✅︎ |
| `Llama4ForConditionalGeneration` | Llama 4 | T + I<sup>+</sup> | `meta-llama/Llama-4-Scout-17B-16E-Instruct`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`, `meta-llama/Llama-4-Maverick-17B-128E-Instruct`, etc. | | ✅︎ | ✅︎ |
| `LlavaForConditionalGeneration` | LLaVA-1.5 | T + I<sup>E+</sup> | `llava-hf/llava-1.5-7b-hf`, `TIGER-Lab/Mantis-8B-siglip-llama3` (see note), etc. | | ✅︎ | ✅︎ |
| `LlavaNextForConditionalGeneration` | LLaVA-NeXT | T + I<sup>E+</sup> | `llava-hf/llava-v1.6-mistral-7b-hf`, `llava-hf/llava-v1.6-vicuna-7b-hf`, etc. | | ✅︎ | ✅︎ |
| `LlavaNextVideoForConditionalGeneration` | LLaVA-NeXT-Video | T + V | `llava-hf/LLaVA-NeXT-Video-7B-hf`, etc. | | ✅︎ | ✅︎ |
| `LlavaOnevisionForConditionalGeneration` | LLaVA-Onevision | T + I<sup>+</sup> + V<sup>+</sup> | `llava-hf/llava-onevision-qwen2-7b-ov-hf`, `llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc. | | ✅︎ | ✅︎ |
| `MiniCPMO` | MiniCPM-O | T + I<sup>E+</sup> + V<sup>E+</sup> + A<sup>E+</sup> | `openbmb/MiniCPM-o-2_6`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MiniCPMV` | MiniCPM-V | T + I<sup>E+</sup> + V<sup>E+</sup> | `openbmb/MiniCPM-V-2` (see note), `openbmb/MiniCPM-Llama3-V-2_5`, `openbmb/MiniCPM-V-2_6`, etc. | ✅︎ | | ✅︎ |
| `MiniMaxVL01ForConditionalGeneration` | MiniMax-VL | T + I<sup>E+</sup> | `MiniMaxAI/MiniMax-VL-01`, etc. | | ✅︎ | |
| `MiniCPMV` | MiniCPM-V | T + I<sup>E+</sup> + V<sup>E+</sup> | `openbmb/MiniCPM-V-2` (see note), `openbmb/MiniCPM-Llama3-V-2_5`, `openbmb/MiniCPM-V-2_6`, etc. | ✅︎ | | ✅︎ |
| `MiniMaxVL01ForConditionalGeneration` | MiniMax-VL | T + I<sup>E+</sup> | `MiniMaxAI/MiniMax-VL-01`, etc. | | ✅︎ | ✅︎ |
| `Mistral3ForConditionalGeneration` | Mistral3 | T + I<sup>+</sup> | `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MllamaForConditionalGeneration` | Llama 3.2 | T + I<sup>+</sup> | `meta-llama/Llama-3.2-90B-Vision-Instruct`, `meta-llama/Llama-3.2-11B-Vision`, etc. | | | |
| `MllamaForConditionalGeneration` | Llama 3.2 | T + I<sup>+</sup> | `meta-llama/Llama-3.2-90B-Vision-Instruct`, `meta-llama/Llama-3.2-11B-Vision`, etc. | | | |
| `MolmoForCausalLM` | Molmo | T + I<sup>+</sup> | `allenai/Molmo-7B-D-0924`, `allenai/Molmo-7B-O-0924`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `NVLM_D_Model` | NVLM-D 1.0 | T + I<sup>+</sup> | `nvidia/NVLM-D-72B`, etc. | | ✅︎ | ✅︎ |
| `Ovis` | Ovis2, Ovis1.6 | T + I<sup>+</sup> | `AIDC-AI/Ovis2-1B`, `AIDC-AI/Ovis1.6-Llama3.2-3B`, etc. | | ✅︎ | ✅︎ |
| `PaliGemmaForConditionalGeneration` | PaliGemma, PaliGemma 2 | T + I<sup>E</sup> | `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc. | | ✅︎ | ⚠️ |
| `Phi3VForCausalLM` | Phi-3-Vision, Phi-3.5-Vision | T + I<sup>E+</sup> | `microsoft/Phi-3-vision-128k-instruct`, `microsoft/Phi-3.5-vision-instruct`, etc. | | ✅︎ | ✅︎ |
| `Phi4MMForCausalLM` | Phi-4-multimodal | T + I<sup>+</sup> / T + A<sup>+</sup> / I<sup>+</sup> + A<sup>+</sup> | `microsoft/Phi-4-multimodal-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `PixtralForConditionalGeneration` | Pixtral | T + I<sup>+</sup> | `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, `mistral-community/pixtral-12b`, etc. | | ✅︎ | ✅︎ |
| `NVLM_D_Model` | NVLM-D 1.0 | T + I<sup>+</sup> | `nvidia/NVLM-D-72B`, etc. | | ✅︎ | ✅︎ |
| `Ovis` | Ovis2, Ovis1.6 | T + I<sup>+</sup> | `AIDC-AI/Ovis2-1B`, `AIDC-AI/Ovis1.6-Llama3.2-3B`, etc. | | ✅︎ | ✅︎ |
| `PaliGemmaForConditionalGeneration` | PaliGemma, PaliGemma 2 | T + I<sup>E</sup> | `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc. | | ✅︎ | ⚠️ |
| `Phi3VForCausalLM` | Phi-3-Vision, Phi-3.5-Vision | T + I<sup>E+</sup> | `microsoft/Phi-3-vision-128k-instruct`, `microsoft/Phi-3.5-vision-instruct`, etc. | | ✅︎ | ✅︎ |
| `Phi4MMForCausalLM` | Phi-4-multimodal | T + I<sup>+</sup> / T + A<sup>+</sup> / I<sup>+</sup> + A<sup>+</sup> | `microsoft/Phi-4-multimodal-instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `PixtralForConditionalGeneration` | Pixtral | T + I<sup>+</sup> | `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, `mistral-community/pixtral-12b`, etc. | | ✅︎ | ✅︎ |
| `QwenVLForConditionalGeneration`<sup>^</sup> | Qwen-VL | T + I<sup>E+</sup> | `Qwen/Qwen-VL`, `Qwen/Qwen-VL-Chat`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2AudioForConditionalGeneration` | Qwen2-Audio | T + A<sup>+</sup> | `Qwen/Qwen2-Audio-7B-Instruct` | | ✅︎ | ✅︎ |
| `Qwen2AudioForConditionalGeneration` | Qwen2-Audio | T + A<sup>+</sup> | `Qwen/Qwen2-Audio-7B-Instruct` | | ✅︎ | ✅︎ |
| `Qwen2VLForConditionalGeneration` | QVQ, Qwen2-VL | T + I<sup>E+</sup> + V<sup>E+</sup> | `Qwen/QVQ-72B-Preview`, `Qwen/Qwen2-VL-7B-Instruct`, `Qwen/Qwen2-VL-72B-Instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2_5_VLForConditionalGeneration` | Qwen2.5-VL | T + I<sup>E+</sup> + V<sup>E+</sup> | `Qwen/Qwen2.5-VL-3B-Instruct`, `Qwen/Qwen2.5-VL-72B-Instruct`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2_5OmniThinkerForConditionalGeneration` | Qwen2.5-Omni | T + I<sup>E+</sup> + V<sup>E+</sup> + A<sup>+</sup> | `Qwen/Qwen2.5-Omni-7B` | | ✅︎ | ✅︎\* |
| `SkyworkR1VChatModel` | Skywork-R1V-38B | T + I | `Skywork/Skywork-R1V-38B` | | ✅︎ | ✅︎ |
| `SmolVLMForConditionalGeneration` | SmolVLM2 | T + I | `SmolVLM2-2.2B-Instruct` | ✅︎ | | ✅︎ |
| `TarsierForConditionalGeneration` | Tarsier | T + I<sup>E+</sup> | `omni-search/Tarsier-7b`,`omni-search/Tarsier-34b` | | ✅︎ | ✅︎ |
| `Qwen2_5OmniThinkerForConditionalGeneration` | Qwen2.5-Omni | T + I<sup>E+</sup> + V<sup>E+</sup> + A<sup>+</sup> | `Qwen/Qwen2.5-Omni-7B` | | ✅︎ | ✅︎\* |
| `SkyworkR1VChatModel` | Skywork-R1V-38B | T + I | `Skywork/Skywork-R1V-38B` | | ✅︎ | ✅︎ |
| `SmolVLMForConditionalGeneration` | SmolVLM2 | T + I | `SmolVLM2-2.2B-Instruct` | ✅︎ | | ✅︎ |
| `TarsierForConditionalGeneration` | Tarsier | T + I<sup>E+</sup> | `omni-search/Tarsier-7b`,`omni-search/Tarsier-34b` | | ✅︎ | ✅︎ |
| `Tarsier2ForConditionalGeneration`<sup>^</sup> | Tarsier2 | T + I<sup>E+</sup> + V<sup>E+</sup> | `omni-research/Tarsier2-Recap-7b`,`omni-research/Tarsier2-7b-0115` | | ✅︎ | ✅︎ |
<sup>^</sup> You need to set the architecture name via `--hf-overrides` to match the one in vLLM.
&nbsp;&nbsp;&nbsp;&nbsp;• For example, to use DeepSeek-VL2 series models:
......@@ -579,9 +626,6 @@ Specified using `--task generate`.
!!! note
Only `InternVLChatModel` with Qwen2.5 text backbone (`OpenGVLab/InternVL3-2B`, `OpenGVLab/InternVL2.5-1B` etc) has video inputs support currently.
!!! note
`h2oai/h2ovl-mississippi-2b` will be available in V1 once we support head size 80.
!!! note
To use `TIGER-Lab/Mantis-8B-siglip-llama3`, you have to pass `--hf_overrides '{"architectures": ["MantisForConditionalGeneration"]}'` when running vLLM.
......@@ -590,27 +634,29 @@ Specified using `--task generate`.
For the best results, we recommend using the following dependency versions (tested on A10 and L40):
```text
# Core vLLM-compatible dependencies with Molmo accuracy setup (tested on L40)
torch==2.5.1
torchvision==0.20.1
transformers==4.48.1
tokenizers==0.21.0
tiktoken==0.7.0
vllm==0.7.0
# Optional but recommended for improved performance and stability
triton==3.1.0
xformers==0.0.28.post3
uvloop==0.21.0
protobuf==5.29.3
openai==1.60.2
opencv-python-headless==4.11.0.86
pillow==10.4.0
# Installed FlashAttention (for float16 only)
flash-attn>=2.5.6 # Not used in float32, but should be documented
```
??? Dependency versions
```text
# Core vLLM-compatible dependencies with Molmo accuracy setup (tested on L40)
torch==2.5.1
torchvision==0.20.1
transformers==4.48.1
tokenizers==0.21.0
tiktoken==0.7.0
vllm==0.7.0
# Optional but recommended for improved performance and stability
triton==3.1.0
xformers==0.0.28.post3
uvloop==0.21.0
protobuf==5.29.3
openai==1.60.2
opencv-python-headless==4.11.0.86
pillow==10.4.0
# Installed FlashAttention (for float16 only)
flash-attn>=2.5.6 # Not used in float32, but should be documented
```
**Note:** Make sure you understand the security implications of using outdated packages.
......@@ -622,17 +668,24 @@ Specified using `--task generate`.
Our PaliGemma implementations have the same problem as Gemma 3 (see above) for both V0 and V1.
!!! note
To use Qwen2.5-Omni, you have to install Hugging Face Transformers library from source via
`pip install git+https://github.com/huggingface/transformers.git`.
For Qwen2.5-Omni, reading audio from video pre-processing (`--mm-processor-kwargs '{"use_audio_in_video": true}'`)
is currently supported on V0 (but not V1), because overlapping modalities is not yet supported in V1.
Read audio from video pre-processing is currently supported on V0 (but not V1), because overlapping modalities is not yet supported in V1.
`--mm-processor-kwargs '{"use_audio_in_video": true}'`.
#### Transcription
Specified using `--task transcription`.
Speech2Text models trained specifically for Automatic Speech Recognition.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|----------------------------------------------|------------------|------------------------------------------------------------------|------------------------|-----------------------------|-----------------------|
| `WhisperForConditionalGeneration` | Whisper | `openai/whisper-small`, `openai/whisper-large-v3-turbo`, etc. | | | |
### Pooling Models
See [this page](./pooling_models.md) for more information on how to use pooling models.
!!! warning
!!! important
Since some model architectures support both generative and pooling tasks,
you should explicitly specify the task type to ensure that the model is used in pooling mode instead of generative mode.
......@@ -647,19 +700,10 @@ Any text generation model can be converted into an embedding model by passing `-
The following table lists those that are tested in vLLM.
| Architecture | Models | Inputs | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|-------------------------------------|--------------------|----------|--------------------------|------------------------|-----------------------------|
| `LlavaNextForConditionalGeneration` | LLaVA-NeXT-based | T / I | `royokong/e5-v` | | |
| `Phi3VForCausalLM` | Phi-3-Vision-based | T + I | `TIGER-Lab/VLM2Vec-Full` | 🚧 | ✅︎ |
#### Transcription
Specified using `--task transcription`.
Speech2Text models trained specifically for Automatic Speech Recognition.
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] |
|----------------|----------|---------------------|------------------------|-----------------------------|
| Architecture | Models | Inputs | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
|-------------------------------------|--------------------|----------|--------------------------|------------------------|-----------------------------|-----------------------|
| `LlavaNextForConditionalGeneration` | LLaVA-NeXT-based | T / I | `royokong/e5-v` | | | |
| `Phi3VForCausalLM` | Phi-3-Vision-based | T + I | `TIGER-Lab/VLM2Vec-Full` | 🚧 | ✅︎ | |
---
......
docs/serving/distributed_serving.md
View file @ 99324e25
......@@ -34,15 +34,15 @@ output = llm.generate("San Francisco is a")
To run multi-GPU serving, pass in the `--tensor-parallel-size` argument when starting the server. For example, to run API server on 4 GPUs:
```console
vllm serve facebook/opt-13b \
```bash
vllm serve facebook/opt-13b \
--tensor-parallel-size 4
```
You can also additionally specify `--pipeline-parallel-size` to enable pipeline parallelism. For example, to run API server on 8 GPUs with pipeline parallelism and tensor parallelism:
```console
vllm serve gpt2 \
```bash
vllm serve gpt2 \
--tensor-parallel-size 4 \
--pipeline-parallel-size 2
```
......@@ -55,7 +55,7 @@ The first step, is to start containers and organize them into a cluster. We have
Pick a node as the head node, and run the following command:
```console
```bash
bash run_cluster.sh \
vllm/vllm-openai \
ip_of_head_node \
......@@ -66,7 +66,7 @@ bash run_cluster.sh \
On the rest of the worker nodes, run the following command:
```console
```bash
bash run_cluster.sh \
vllm/vllm-openai \
ip_of_head_node \
......@@ -87,7 +87,7 @@ Then, on any node, use `docker exec -it node /bin/bash` to enter the container,
After that, on any node, use `docker exec -it node /bin/bash` to enter the container again. **In the container**, you can use vLLM as usual, just as you have all the GPUs on one node: vLLM will be able to leverage GPU resources of all nodes in the Ray cluster, and therefore, only run the `vllm` command on this node but not other nodes. The common practice is to set the tensor parallel size to the number of GPUs in each node, and the pipeline parallel size to the number of nodes. For example, if you have 16 GPUs in 2 nodes (8 GPUs per node), you can set the tensor parallel size to 8 and the pipeline parallel size to 2:
```console
```bash
vllm serve /path/to/the/model/in/the/container \
--tensor-parallel-size 8 \
--pipeline-parallel-size 2
......@@ -95,12 +95,55 @@ After that, on any node, use `docker exec -it node /bin/bash` to enter the conta
You can also use tensor parallel without pipeline parallel, just set the tensor parallel size to the number of GPUs in the cluster. For example, if you have 16 GPUs in 2 nodes (8 GPUs per node), you can set the tensor parallel size to 16:
```console
```bash
vllm serve /path/to/the/model/in/the/container \
--tensor-parallel-size 16
```
To make tensor parallel performant, you should make sure the communication between nodes is efficient, e.g. using high-speed network cards like Infiniband. To correctly set up the cluster to use Infiniband, append additional arguments like `--privileged -e NCCL_IB_HCA=mlx5` to the `run_cluster.sh` script. Please contact your system administrator for more information on how to set up the flags. One way to confirm if the Infiniband is working is to run vLLM with `NCCL_DEBUG=TRACE` environment variable set, e.g. `NCCL_DEBUG=TRACE vllm serve ...` and check the logs for the NCCL version and the network used. If you find `[send] via NET/Socket` in the logs, it means NCCL uses raw TCP Socket, which is not efficient for cross-node tensor parallel. If you find `[send] via NET/IB/GDRDMA` in the logs, it means NCCL uses Infiniband with GPU-Direct RDMA, which is efficient.
To make tensor parallel performant, you should make sure the communication between nodes is efficient, e.g. using high-speed network cards like InfiniBand. To correctly set up the cluster to use InfiniBand, append additional arguments like `--privileged -e NCCL_IB_HCA=mlx5` to the `run_cluster.sh` script. Please contact your system administrator for more information on how to set up the flags. One way to confirm if the InfiniBand is working is to run vLLM with `NCCL_DEBUG=TRACE` environment variable set, e.g. `NCCL_DEBUG=TRACE vllm serve ...` and check the logs for the NCCL version and the network used. If you find `[send] via NET/Socket` in the logs, it means NCCL uses raw TCP Socket, which is not efficient for cross-node tensor parallel. If you find `[send] via NET/IB/GDRDMA` in the logs, it means NCCL uses InfiniBand with GPUDirect RDMA, which is efficient.
### GPUDirect RDMA
To enable GPUDirect RDMA with vLLM, specific configuration tweaks are needed. This setup ensures:
- `IPC_LOCK` Security Context: Add the `IPC_LOCK` capability to the container’s security context to lock memory pages and prevent swapping to disk.
- Shared Memory with `/dev/shm`: Mount `/dev/shm` in the pod spec to provide shared memory for IPC.
When using Docker, you can set up the container as follows:
```bash
docker run --gpus all \
--ipc=host \
--shm-size=16G \
-v /dev/shm:/dev/shm \
vllm/vllm-openai
```
When using Kubernetes, you can set up the pod spec as follows:
```yaml
...
spec:
containers:
- name: vllm
image: vllm/vllm-openai
securityContext:
capabilities:
add: ["IPC_LOCK"]
volumeMounts:
- mountPath: /dev/shm
name: dshm
resources:
limits:
nvidia.com/gpu: 8
requests:
nvidia.com/gpu: 8
volumes:
- name: dshm
emptyDir:
medium: Memory
...
```
!!! warning
After you start the Ray cluster, you'd better also check the GPU-GPU communication between nodes. It can be non-trivial to set up. Please refer to the [sanity check script][troubleshooting-incorrect-hardware-driver] for more information. If you need to set some environment variables for the communication configuration, you can append them to the `run_cluster.sh` script, e.g. `-e NCCL_SOCKET_IFNAME=eth0`. Note that setting environment variables in the shell (e.g. `NCCL_SOCKET_IFNAME=eth0 vllm serve ...`) only works for the processes in the same node, not for the processes in the other nodes. Setting environment variables when you create the cluster is the recommended way. See <gh-issue:6803> for more information.
......
docs/serving/integrations/langchain.md
View file @ 99324e25
......@@ -7,25 +7,27 @@ vLLM is also available via [LangChain](https://github.com/langchain-ai/langchain
To install LangChain, run
```console
```bash
pip install langchain langchain_community -q
```
To run inference on a single or multiple GPUs, use `VLLM` class from `langchain`.
```python
from langchain_community.llms import VLLM
??? Code
llm = VLLM(model="mosaicml/mpt-7b",
trust_remote_code=True, # mandatory for hf models
max_new_tokens=128,
top_k=10,
top_p=0.95,
temperature=0.8,
# tensor_parallel_size=... # for distributed inference
)
```python
from langchain_community.llms import VLLM
print(llm("What is the capital of France ?"))
```
llm = VLLM(model="mosaicml/mpt-7b",
trust_remote_code=True, # mandatory for hf models
max_new_tokens=128,
top_k=10,
top_p=0.95,
temperature=0.8,
# tensor_parallel_size=... # for distributed inference
)
print(llm("What is the capital of France ?"))
```
Please refer to this [Tutorial](https://python.langchain.com/docs/integrations/llms/vllm) for more details.
docs/serving/integrations/llamaindex.md
View file @ 99324e25
......@@ -7,7 +7,7 @@ vLLM is also available via [LlamaIndex](https://github.com/run-llama/llama_index
To install LlamaIndex, run
```console
```bash
pip install llama-index-llms-vllm -q
```
......
docs/serving/openai_compatible_server.md
View file @ 99324e25
---
title: OpenAI-Compatible Server
---
[](){ #openai-compatible-server }
[](){ #serving-openai-compatible-server }
vLLM provides an HTTP server that implements OpenAI's [Completions API](https://platform.openai.com/docs/api-reference/completions), [Chat API](https://platform.openai.com/docs/api-reference/chat), and more! This functionality lets you serve models and interact with them using an HTTP client.
......@@ -15,28 +15,30 @@ vllm serve NousResearch/Meta-Llama-3-8B-Instruct \
To call the server, in your preferred text editor, create a script that uses an HTTP client. Include any messages that you want to send to the model. Then run that script. Below is an example script using the [official OpenAI Python client](https://github.com/openai/openai-python).
```python
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:8000/v1",
api_key="token-abc123",
)
??? Code
completion = client.chat.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
messages=[
{"role": "user", "content": "Hello!"}
]
)
```python
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:8000/v1",
api_key="token-abc123",
)
print(completion.choices[0].message)
```
completion = client.chat.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(completion.choices[0].message)
```
!!! tip
vLLM supports some parameters that are not supported by OpenAI, `top_k` for example.
You can pass these parameters to vLLM using the OpenAI client in the `extra_body` parameter of your requests, i.e. `extra_body={"top_k": 50}` for `top_k`.
!!! warning
!!! important
By default, the server applies `generation_config.json` from the Hugging Face model repository if it exists. This means the default values of certain sampling parameters can be overridden by those recommended by the model creator.
To disable this behavior, please pass `--generation-config vllm` when launching the server.
......@@ -55,6 +57,8 @@ We currently support the following OpenAI APIs:
- Only applicable to [embedding models](../models/pooling_models.md) (`--task embed`).
- [Transcriptions API][transcriptions-api] (`/v1/audio/transcriptions`)
- Only applicable to Automatic Speech Recognition (ASR) models (OpenAI Whisper) (`--task generate`).
- [Translation API][translations-api] (`/v1/audio/translations`)
- Only applicable to Automatic Speech Recognition (ASR) models (OpenAI Whisper) (`--task generate`).
In addition, we have the following custom APIs:
......@@ -142,32 +146,29 @@ completion = client.chat.completions.create(
Only `X-Request-Id` HTTP request header is supported for now. It can be enabled
with `--enable-request-id-headers`.
> Note that enablement of the headers can impact performance significantly at high QPS
> rates. We recommend implementing HTTP headers at the router level (e.g. via Istio),
> rather than within the vLLM layer for this reason.
> See [this PR](https://github.com/vllm-project/vllm/pull/11529) for more details.
??? Code
```python
completion = client.chat.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
messages=[
{"role": "user", "content": "Classify this sentiment: vLLM is wonderful!"}
],
extra_headers={
"x-request-id": "sentiment-classification-00001",
}
)
print(completion._request_id)
completion = client.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
prompt="A robot may not injure a human being",
extra_headers={
"x-request-id": "completion-test",
}
)
print(completion._request_id)
```
```python
completion = client.chat.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
messages=[
{"role": "user", "content": "Classify this sentiment: vLLM is wonderful!"}
],
extra_headers={
"x-request-id": "sentiment-classification-00001",
}
)
print(completion._request_id)
completion = client.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
prompt="A robot may not injure a human being",
extra_headers={
"x-request-id": "completion-test",
}
)
print(completion._request_id)
```
## API Reference
......@@ -184,15 +185,19 @@ Code example: <gh-file:examples/online_serving/openai_completion_client.py>
The following [sampling parameters][sampling-params] are supported.
```python
--8<-- "vllm/entrypoints/openai/protocol.py:completion-sampling-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:completion-sampling-params"
```
The following extra parameters are supported:
```python
--8<-- "vllm/entrypoints/openai/protocol.py:completion-extra-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:completion-extra-params"
```
[](){ #chat-api }
......@@ -212,15 +217,19 @@ Code example: <gh-file:examples/online_serving/openai_chat_completion_client.py>
The following [sampling parameters][sampling-params] are supported.
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-completion-sampling-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-completion-sampling-params"
```
The following extra parameters are supported:
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-completion-extra-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-completion-extra-params"
```
[](){ #embeddings-api }
......@@ -250,7 +259,7 @@ and passing a list of `messages` in the request. Refer to the examples below for
--chat-template examples/template_vlm2vec.jinja
```
!!! warning
!!! important
Since VLM2Vec has the same model architecture as Phi-3.5-Vision, we have to explicitly pass `--task embed`
to run this model in embedding mode instead of text generation mode.
......@@ -259,29 +268,31 @@ and passing a list of `messages` in the request. Refer to the examples below for
Since the request schema is not defined by OpenAI client, we post a request to the server using the lower-level `requests` library:
```python
import requests
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
response = requests.post(
"http://localhost:8000/v1/embeddings",
json={
"model": "TIGER-Lab/VLM2Vec-Full",
"messages": [{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": image_url}},
{"type": "text", "text": "Represent the given image."},
],
}],
"encoding_format": "float",
},
)
response.raise_for_status()
response_json = response.json()
print("Embedding output:", response_json["data"][0]["embedding"])
```
??? Code
```python
import requests
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
response = requests.post(
"http://localhost:8000/v1/embeddings",
json={
"model": "TIGER-Lab/VLM2Vec-Full",
"messages": [{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": image_url}},
{"type": "text", "text": "Represent the given image."},
],
}],
"encoding_format": "float",
},
)
response.raise_for_status()
response_json = response.json()
print("Embedding output:", response_json["data"][0]["embedding"])
```
=== "DSE-Qwen2-MRL"
......@@ -294,13 +305,13 @@ and passing a list of `messages` in the request. Refer to the examples below for
--chat-template examples/template_dse_qwen2_vl.jinja
```
!!! warning
!!! important
Like with VLM2Vec, we have to explicitly pass `--task embed`.
Additionally, `MrLight/dse-qwen2-2b-mrl-v1` requires an EOS token for embeddings, which is handled
by a custom chat template: <gh-file:examples/template_dse_qwen2_vl.jinja>
!!! warning
!!! important
`MrLight/dse-qwen2-2b-mrl-v1` requires a placeholder image of the minimum image size for text query embeddings. See the full code
example below for details.
......@@ -316,15 +327,19 @@ The following [pooling parameters][pooling-params] are supported.
The following extra parameters are supported by default:
```python
--8<-- "vllm/entrypoints/openai/protocol.py:embedding-extra-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:embedding-extra-params"
```
For chat-like input (i.e. if `messages` is passed), these extra parameters are supported instead:
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-embedding-extra-params"
```
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:chat-embedding-extra-params"
```
[](){ #transcriptions-api }
......@@ -343,14 +358,46 @@ Code example: <gh-file:examples/online_serving/openai_transcription_client.py>
The following [sampling parameters][sampling-params] are supported.
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:transcription-sampling-params"
```
The following extra parameters are supported:
??? Code
```python
--8<-- "vllm/entrypoints/openai/protocol.py:transcription-extra-params"
```
[](){ #translations-api }
### Translations API
Our Translation API is compatible with [OpenAI's Translations API](https://platform.openai.com/docs/api-reference/audio/createTranslation);
you can use the [official OpenAI Python client](https://github.com/openai/openai-python) to interact with it.
Whisper models can translate audio from one of the 55 non-English supported languages into English.
Please mind that the popular `openai/whisper-large-v3-turbo` model does not support translating.
!!! note
To use the Translation API, please install with extra audio dependencies using `pip install vllm[audio]`.
Code example: <gh-file:examples/online_serving/openai_translation_client.py>
#### Extra Parameters
The following [sampling parameters][sampling-params] are supported.
```python
--8<-- "vllm/entrypoints/openai/protocol.py:transcription-sampling-params"
--8<-- "vllm/entrypoints/openai/protocol.py:translation-sampling-params"
```
The following extra parameters are supported:
```python
--8<-- "vllm/entrypoints/openai/protocol.py:transcription-extra-params"
--8<-- "vllm/entrypoints/openai/protocol.py:translation-extra-params"
```
[](){ #tokenizer-api }
......@@ -379,7 +426,7 @@ Code example: <gh-file:examples/online_serving/openai_pooling_client.py>
Our Classification API directly supports Hugging Face sequence-classification models such as [ai21labs/Jamba-tiny-reward-dev](https://huggingface.co/ai21labs/Jamba-tiny-reward-dev) and [jason9693/Qwen2.5-1.5B-apeach](https://huggingface.co/jason9693/Qwen2.5-1.5B-apeach).
We automatically wrap any other transformer via `as_classification_model()`, which pools on the last token, attaches a `RowParallelLinear` head, and applies a softmax to produce per-class probabilities.
We automatically wrap any other transformer via `as_seq_cls_model()`, which pools on the last token, attaches a `RowParallelLinear` head, and applies a softmax to produce per-class probabilities.
Code example: <gh-file:examples/online_serving/openai_classification_client.py>
......@@ -387,8 +434,6 @@ Code example: <gh-file:examples/online_serving/openai_classification_client.py>
You can classify multiple texts by passing an array of strings:
Request:
```bash
curl -v "http://127.0.0.1:8000/classify" \
-H "Content-Type: application/json" \
......@@ -401,47 +446,45 @@ curl -v "http://127.0.0.1:8000/classify" \
}'
```
Response:
??? Response
```bash
{
"id": "classify-7c87cac407b749a6935d8c7ce2a8fba2",
"object": "list",
"created": 1745383065,
"model": "jason9693/Qwen2.5-1.5B-apeach",
"data": [
{
"index": 0,
"label": "Default",
"probs": [
0.565970778465271,
0.4340292513370514
],
"num_classes": 2
},
```bash
{
"index": 1,
"label": "Spoiled",
"probs": [
0.26448777318000793,
0.7355121970176697
"id": "classify-7c87cac407b749a6935d8c7ce2a8fba2",
"object": "list",
"created": 1745383065,
"model": "jason9693/Qwen2.5-1.5B-apeach",
"data": [
{
"index": 0,
"label": "Default",
"probs": [
0.565970778465271,
0.4340292513370514
],
"num_classes": 2
},
{
"index": 1,
"label": "Spoiled",
"probs": [
0.26448777318000793,
0.7355121970176697
],
"num_classes": 2
}
],
"num_classes": 2
"usage": {
"prompt_tokens": 20,
"total_tokens": 20,
"completion_tokens": 0,
"prompt_tokens_details": null
}
}
],
"usage": {
"prompt_tokens": 20,
"total_tokens": 20,
"completion_tokens": 0,
"prompt_tokens_details": null
}
}
```
```
You can also pass a string directly to the `input` field:
Request:
```bash
curl -v "http://127.0.0.1:8000/classify" \
-H "Content-Type: application/json" \
......@@ -451,33 +494,33 @@ curl -v "http://127.0.0.1:8000/classify" \
}'
```
Response:
??? Response
```bash
{
"id": "classify-9bf17f2847b046c7b2d5495f4b4f9682",
"object": "list",
"created": 1745383213,
"model": "jason9693/Qwen2.5-1.5B-apeach",
"data": [
```bash
{
"index": 0,
"label": "Default",
"probs": [
0.565970778465271,
0.4340292513370514
"id": "classify-9bf17f2847b046c7b2d5495f4b4f9682",
"object": "list",
"created": 1745383213,
"model": "jason9693/Qwen2.5-1.5B-apeach",
"data": [
{
"index": 0,
"label": "Default",
"probs": [
0.565970778465271,
0.4340292513370514
],
"num_classes": 2
}
],
"num_classes": 2
"usage": {
"prompt_tokens": 10,
"total_tokens": 10,
"completion_tokens": 0,
"prompt_tokens_details": null
}
}
],
"usage": {
"prompt_tokens": 10,
"total_tokens": 10,
"completion_tokens": 0,
"prompt_tokens_details": null
}
}
```
```
#### Extra parameters
......@@ -508,8 +551,6 @@ Code example: <gh-file:examples/online_serving/openai_cross_encoder_score.py>
You can pass a string to both `text_1` and `text_2`, forming a single sentence pair.
Request:
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/score' \
......@@ -523,24 +564,24 @@ curl -X 'POST' \
}'
```
Response:
??? Response
```bash
{
"id": "score-request-id",
"object": "list",
"created": 693447,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
```bash
{
"index": 0,
"object": "score",
"score": 1
"id": "score-request-id",
"object": "list",
"created": 693447,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
{
"index": 0,
"object": "score",
"score": 1
}
],
"usage": {}
}
],
"usage": {}
}
```
```
#### Batch inference
......@@ -548,95 +589,95 @@ You can pass a string to `text_1` and a list to `text_2`, forming multiple sente
where each pair is built from `text_1` and a string in `text_2`.
The total number of pairs is `len(text_2)`.
Request:
??? Request
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/score' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-v2-m3",
"text_1": "What is the capital of France?",
"text_2": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris."
]
}'
```
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/score' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-v2-m3",
"text_1": "What is the capital of France?",
"text_2": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris."
]
}'
```
Response:
??? Response
```bash
{
"id": "score-request-id",
"object": "list",
"created": 693570,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
{
"index": 0,
"object": "score",
"score": 0.001094818115234375
},
```bash
{
"index": 1,
"object": "score",
"score": 1
"id": "score-request-id",
"object": "list",
"created": 693570,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
{
"index": 0,
"object": "score",
"score": 0.001094818115234375
},
{
"index": 1,
"object": "score",
"score": 1
}
],
"usage": {}
}
],
"usage": {}
}
```
```
You can pass a list to both `text_1` and `text_2`, forming multiple sentence pairs
where each pair is built from a string in `text_1` and the corresponding string in `text_2` (similar to `zip()`).
The total number of pairs is `len(text_2)`.
Request:
??? Request
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/score' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-v2-m3",
"encoding_format": "float",
"text_1": [
"What is the capital of Brazil?",
"What is the capital of France?"
],
"text_2": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris."
]
}'
```
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/score' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-v2-m3",
"encoding_format": "float",
"text_1": [
"What is the capital of Brazil?",
"What is the capital of France?"
],
"text_2": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris."
]
}'
```
Response:
??? Response
```bash
{
"id": "score-request-id",
"object": "list",
"created": 693447,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
{
"index": 0,
"object": "score",
"score": 1
},
```bash
{
"index": 1,
"object": "score",
"score": 1
"id": "score-request-id",
"object": "list",
"created": 693447,
"model": "BAAI/bge-reranker-v2-m3",
"data": [
{
"index": 0,
"object": "score",
"score": 1
},
{
"index": 1,
"object": "score",
"score": 1
}
],
"usage": {}
}
],
"usage": {}
}
```
```
#### Extra parameters
......@@ -675,51 +716,51 @@ Code example: <gh-file:examples/online_serving/jinaai_rerank_client.py>
Note that the `top_n` request parameter is optional and will default to the length of the `documents` field.
Result documents will be sorted by relevance, and the `index` property can be used to determine original order.
Request:
??? Request
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/v1/rerank' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-base",
"query": "What is the capital of France?",
"documents": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris.",
"Horses and cows are both animals"
]
}'
```
```bash
curl -X 'POST' \
'http://127.0.0.1:8000/v1/rerank' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "BAAI/bge-reranker-base",
"query": "What is the capital of France?",
"documents": [
"The capital of Brazil is Brasilia.",
"The capital of France is Paris.",
"Horses and cows are both animals"
]
}'
```
Response:
??? Response
```bash
{
"id": "rerank-fae51b2b664d4ed38f5969b612edff77",
"model": "BAAI/bge-reranker-base",
"usage": {
"total_tokens": 56
},
"results": [
{
"index": 1,
"document": {
"text": "The capital of France is Paris."
},
"relevance_score": 0.99853515625
},
```bash
{
"index": 0,
"document": {
"text": "The capital of Brazil is Brasilia."
"id": "rerank-fae51b2b664d4ed38f5969b612edff77",
"model": "BAAI/bge-reranker-base",
"usage": {
"total_tokens": 56
},
"relevance_score": 0.0005860328674316406
"results": [
{
"index": 1,
"document": {
"text": "The capital of France is Paris."
},
"relevance_score": 0.99853515625
},
{
"index": 0,
"document": {
"text": "The capital of Brazil is Brasilia."
},
"relevance_score": 0.0005860328674316406
}
]
}
]
}
```
```
#### Extra parameters
......
docs/usage/metrics.md
View file @ 99324e25
......@@ -6,34 +6,38 @@ OpenAI compatible API server.
You can start the server using Python, or using [Docker][deployment-docker]:
```console
```bash
vllm serve unsloth/Llama-3.2-1B-Instruct
```
Then query the endpoint to get the latest metrics from the server:
```console
$ curl http://0.0.0.0:8000/metrics
# HELP vllm:iteration_tokens_total Histogram of number of tokens per engine_step.
# TYPE vllm:iteration_tokens_total histogram
vllm:iteration_tokens_total_sum{model_name="unsloth/Llama-3.2-1B-Instruct"} 0.0
vllm:iteration_tokens_total_bucket{le="1.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="8.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="16.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="32.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="64.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="128.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="256.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="512.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
...
```
??? Output
```console
$ curl http://0.0.0.0:8000/metrics
# HELP vllm:iteration_tokens_total Histogram of number of tokens per engine_step.
# TYPE vllm:iteration_tokens_total histogram
vllm:iteration_tokens_total_sum{model_name="unsloth/Llama-3.2-1B-Instruct"} 0.0
vllm:iteration_tokens_total_bucket{le="1.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="8.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="16.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="32.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="64.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="128.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="256.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
vllm:iteration_tokens_total_bucket{le="512.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
...
```
The following metrics are exposed:
```python
--8<-- "vllm/engine/metrics.py:metrics-definitions"
```
??? Code
```python
--8<-- "vllm/engine/metrics.py:metrics-definitions"
```
Note: when metrics are deprecated in version `X.Y`, they are hidden in version `X.Y+1`
but can be re-enabled using the `--show-hidden-metrics-for-version=X.Y` escape hatch,
......
docs/usage/troubleshooting.md
View file @ 99324e25
......@@ -60,79 +60,84 @@ To identify the particular CUDA operation that causes the error, you can add `--
If GPU/CPU communication cannot be established, you can use the following Python script and follow the instructions below to confirm whether the GPU/CPU communication is working correctly.
```python
# Test PyTorch NCCL
import torch
import torch.distributed as dist
dist.init_process_group(backend="nccl")
local_rank = dist.get_rank() % torch.cuda.device_count()
torch.cuda.set_device(local_rank)
data = torch.FloatTensor([1,] * 128).to("cuda")
dist.all_reduce(data, op=dist.ReduceOp.SUM)
torch.cuda.synchronize()
value = data.mean().item()
world_size = dist.get_world_size()
assert value == world_size, f"Expected {world_size}, got {value}"
print("PyTorch NCCL is successful!")
# Test PyTorch GLOO
gloo_group = dist.new_group(ranks=list(range(world_size)), backend="gloo")
cpu_data = torch.FloatTensor([1,] * 128)
dist.all_reduce(cpu_data, op=dist.ReduceOp.SUM, group=gloo_group)
value = cpu_data.mean().item()
assert value == world_size, f"Expected {world_size}, got {value}"
print("PyTorch GLOO is successful!")
if world_size <= 1:
exit()
# Test vLLM NCCL, with cuda graph
from vllm.distributed.device_communicators.pynccl import PyNcclCommunicator
pynccl = PyNcclCommunicator(group=gloo_group, device=local_rank)
# pynccl is enabled by default for 0.6.5+,
# but for 0.6.4 and below, we need to enable it manually.
# keep the code for backward compatibility when because people
# prefer to read the latest documentation.
pynccl.disabled = False
s = torch.cuda.Stream()
with torch.cuda.stream(s):
data.fill_(1)
out = pynccl.all_reduce(data, stream=s)
value = out.mean().item()
??? Code
```python
# Test PyTorch NCCL
import torch
import torch.distributed as dist
dist.init_process_group(backend="nccl")
local_rank = dist.get_rank() % torch.cuda.device_count()
torch.cuda.set_device(local_rank)
data = torch.FloatTensor([1,] * 128).to("cuda")
dist.all_reduce(data, op=dist.ReduceOp.SUM)
torch.cuda.synchronize()
value = data.mean().item()
world_size = dist.get_world_size()
assert value == world_size, f"Expected {world_size}, got {value}"
print("vLLM NCCL is successful!")
print("PyTorch NCCL is successful!")
g = torch.cuda.CUDAGraph()
with torch.cuda.graph(cuda_graph=g, stream=s):
out = pynccl.all_reduce(data, stream=torch.cuda.current_stream())
# Test PyTorch GLOO
gloo_group = dist.new_group(ranks=list(range(world_size)), backend="gloo")
cpu_data = torch.FloatTensor([1,] * 128)
dist.all_reduce(cpu_data, op=dist.ReduceOp.SUM, group=gloo_group)
value = cpu_data.mean().item()
assert value == world_size, f"Expected {world_size}, got {value}"
data.fill_(1)
g.replay()
torch.cuda.current_stream().synchronize()
value = out.mean().item()
assert value == world_size, f"Expected {world_size}, got {value}"
print("PyTorch GLOO is successful!")
print("vLLM NCCL with cuda graph is successful!")
if world_size <= 1:
exit()
dist.destroy_process_group(gloo_group)
dist.destroy_process_group()
```
# Test vLLM NCCL, with cuda graph
from vllm.distributed.device_communicators.pynccl import PyNcclCommunicator
pynccl = PyNcclCommunicator(group=gloo_group, device=local_rank)
# pynccl is enabled by default for 0.6.5+,
# but for 0.6.4 and below, we need to enable it manually.
# keep the code for backward compatibility when because people
# prefer to read the latest documentation.
pynccl.disabled = False
s = torch.cuda.Stream()
with torch.cuda.stream(s):
data.fill_(1)
out = pynccl.all_reduce(data, stream=s)
value = out.mean().item()
assert value == world_size, f"Expected {world_size}, got {value}"
print("vLLM NCCL is successful!")
g = torch.cuda.CUDAGraph()
with torch.cuda.graph(cuda_graph=g, stream=s):
out = pynccl.all_reduce(data, stream=torch.cuda.current_stream())
data.fill_(1)
g.replay()
torch.cuda.current_stream().synchronize()
value = out.mean().item()
assert value == world_size, f"Expected {world_size}, got {value}"
print("vLLM NCCL with cuda graph is successful!")
dist.destroy_process_group(gloo_group)
dist.destroy_process_group()
```
If you are testing with a single node, adjust `--nproc-per-node` to the number of GPUs you want to use:
```console
```bash
NCCL_DEBUG=TRACE torchrun --nproc-per-node=<number-of-GPUs> test.py
```
If you are testing with multi-nodes, adjust `--nproc-per-node` and `--nnodes` according to your setup and set `MASTER_ADDR` to the correct IP address of the master node, reachable from all nodes. Then, run:
```console
NCCL_DEBUG=TRACE torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=$MASTER_ADDR test.py
```bash
NCCL_DEBUG=TRACE torchrun --nnodes 2 \
--nproc-per-node=2 \
--rdzv_backend=c10d \
--rdzv_endpoint=$MASTER_ADDR test.py
```
If the script runs successfully, you should see the message `sanity check is successful!`.
......@@ -165,25 +170,27 @@ WARNING 12-11 14:50:37 multiproc_worker_utils.py:281] CUDA was previously
or an error from Python that looks like this:
```console
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
??? Logs
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
```console
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
if __name__ == '__main__':
freeze_support()
...
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
if __name__ == '__main__':
freeze_support()
...
To fix this issue, refer to the "Safe importing of main module"
section in https://docs.python.org/3/library/multiprocessing.html
```
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
To fix this issue, refer to the "Safe importing of main module"
section in https://docs.python.org/3/library/multiprocessing.html
```
then you must update your Python code to guard usage of `vllm` behind a `if
__name__ == '__main__':` block. For example, instead of this:
......@@ -207,20 +214,22 @@ if __name__ == '__main__':
vLLM heavily depends on `torch.compile` to optimize the model for better performance, which introduces the dependency on the `torch.compile` functionality and the `triton` library. By default, we use `torch.compile` to [optimize some functions](https://github.com/vllm-project/vllm/pull/10406) in the model. Before running vLLM, you can check if `torch.compile` is working as expected by running the following script:
```python
import torch
@torch.compile
def f(x):
# a simple function to test torch.compile
x = x + 1
x = x * 2
x = x.sin()
return x
x = torch.randn(4, 4).cuda()
print(f(x))
```
??? Code
```python
import torch
@torch.compile
def f(x):
# a simple function to test torch.compile
x = x + 1
x = x * 2
x = x.sin()
return x
x = torch.randn(4, 4).cuda()
print(f(x))
```
If it raises errors from `torch/_inductor` directory, usually it means you have a custom `triton` library that is not compatible with the version of PyTorch you are using. See [this issue](https://github.com/vllm-project/vllm/issues/12219) for example.
......@@ -264,6 +273,27 @@ But you are sure that the model is in the [list of supported models][supported-m
If you see an error like `RuntimeError: Failed to infer device type`, it means that vLLM failed to infer the device type of the runtime environment. You can check [the code](gh-file:vllm/platforms/__init__.py) to see how vLLM infers the device type and why it is not working as expected. After [this PR](gh-pr:14195), you can also set the environment variable `VLLM_LOGGING_LEVEL=DEBUG` to see more detailed logs to help debug the issue.
## NCCL error: unhandled system error during `ncclCommInitRank`
If your serving workload uses GPUDirect RDMA for distributed serving across multiple nodes and encounters an error during `ncclCommInitRank`, with no clear error message even with `NCCL_DEBUG=INFO` set, it might look like this:
```text
Error executing method 'init_device'. This might cause deadlock in distributed execution.
Traceback (most recent call last):
...
File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/device_communicators/pynccl.py", line 99, in __init__
self.comm: ncclComm_t = self.nccl.ncclCommInitRank(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/device_communicators/pynccl_wrapper.py", line 277, in ncclCommInitRank
self.NCCL_CHECK(self._funcs["ncclCommInitRank"](ctypes.byref(comm),
File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/device_communicators/pynccl_wrapper.py", line 256, in NCCL_CHECK
raise RuntimeError(f"NCCL error: {error_str}")
RuntimeError: NCCL error: unhandled system error (run with NCCL_DEBUG=INFO for details)
...
```
This indicates vLLM failed to initialize the NCCL communicator, possibly due to a missing `IPC_LOCK` linux capability or an unmounted `/dev/shm`. Refer to [Distributed Inference and Serving](../serving/distributed_serving.md#running-vllm-on-multiple-nodes) for guidance on properly configuring the environment for distributed serving.
## Known Issues
- In `v0.5.2`, `v0.5.3`, and `v0.5.3.post1`, there is a bug caused by [zmq](https://github.com/zeromq/pyzmq/issues/2000) , which can occasionally cause vLLM to hang depending on the machine configuration. The solution is to upgrade to the latest version of `vllm` to include the [fix](gh-pr:6759).
......
docs/usage/usage_stats.md
View file @ 99324e25
......@@ -10,36 +10,38 @@ The list of data collected by the latest version of vLLM can be found here: <gh-
Here is an example as of v0.4.0:
```json
{
"uuid": "fbe880e9-084d-4cab-a395-8984c50f1109",
"provider": "GCP",
"num_cpu": 24,
"cpu_type": "Intel(R) Xeon(R) CPU @ 2.20GHz",
"cpu_family_model_stepping": "6,85,7",
"total_memory": 101261135872,
"architecture": "x86_64",
"platform": "Linux-5.10.0-28-cloud-amd64-x86_64-with-glibc2.31",
"gpu_count": 2,
"gpu_type": "NVIDIA L4",
"gpu_memory_per_device": 23580639232,
"model_architecture": "OPTForCausalLM",
"vllm_version": "0.3.2+cu123",
"context": "LLM_CLASS",
"log_time": 1711663373492490000,
"source": "production",
"dtype": "torch.float16",
"tensor_parallel_size": 1,
"block_size": 16,
"gpu_memory_utilization": 0.9,
"quantization": null,
"kv_cache_dtype": "auto",
"enable_lora": false,
"enable_prefix_caching": false,
"enforce_eager": false,
"disable_custom_all_reduce": true
}
```
??? Output
```json
{
"uuid": "fbe880e9-084d-4cab-a395-8984c50f1109",
"provider": "GCP",
"num_cpu": 24,
"cpu_type": "Intel(R) Xeon(R) CPU @ 2.20GHz",
"cpu_family_model_stepping": "6,85,7",
"total_memory": 101261135872,
"architecture": "x86_64",
"platform": "Linux-5.10.0-28-cloud-amd64-x86_64-with-glibc2.31",
"gpu_count": 2,
"gpu_type": "NVIDIA L4",
"gpu_memory_per_device": 23580639232,
"model_architecture": "OPTForCausalLM",
"vllm_version": "0.3.2+cu123",
"context": "LLM_CLASS",
"log_time": 1711663373492490000,
"source": "production",
"dtype": "torch.float16",
"tensor_parallel_size": 1,
"block_size": 16,
"gpu_memory_utilization": 0.9,
"quantization": null,
"kv_cache_dtype": "auto",
"enable_lora": false,
"enable_prefix_caching": false,
"enforce_eager": false,
"disable_custom_all_reduce": true
}
```
You can preview the collected data by running the following command:
......
docs/usage/v1_guide.md
View file @ 99324e25
# vLLM V1
**We have started the process of deprecating V0. Please read [RFC #18571](https://github.com/vllm-project/vllm/issues/18571) for more details.**
!!! announcement
We have started the process of deprecating V0. Please read [RFC #18571](https://github.com/vllm-project/vllm/issues/18571) for more details.
V1 is now enabled by default for all supported use cases, and we will gradually enable it for every use case we plan to support. Please share any feedback on [GitHub](https://github.com/vllm-project/vllm) or in the [vLLM Slack](https://inviter.co/vllm-slack).
......@@ -32,53 +34,110 @@ Upgrade to vLLM’s Core Architecture](https://blog.vllm.ai/2025/01/27/v1-alpha-
This living user guide outlines a few known **important changes and limitations** introduced by vLLM V1. The team has been working actively to bring V1 as the default engine, therefore this guide will be updated constantly as more features get supported on vLLM V1.
### Supports Overview
#### Hardware
## Current Status
For each item, our progress towards V1 support falls into one of the following states:
- **🚀 Optimized**: Nearly fully optimized, with no further work currently planned.
- **🟢 Functional**: Fully operational, with ongoing optimizations.
- **🚧 WIP**: Under active development.
- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
- **🟠 Delayed**: Temporarily dropped in V1 but planned to be re-introduced later.
- **🔴 Deprecated**: Not planned for V1 unless there is strong demand.
!!! note
vLLM V1’s unified scheduler treats both prompt and output tokens the same
way by using a simple dictionary (e.g., `{request_id: num_tokens}`) to dynamically
allocate a fixed token budget per request, enabling features like chunked prefills,
prefix caching, and speculative decoding without a strict separation between prefill
and decode phases.
The V1 scheduler supports multiple scheduling policies, including First-Come,
First-Served (FCFS) and priority-based scheduling (where requests are processed
based on assigned priority, with FCFS as a tie-breaker), configurable via the
`--scheduling-policy` argument.
### Hardware
| Hardware | Status |
|------------|------------------------------------|
| **NVIDIA** | <nobr>🚀</nobr> |
| **AMD** | <nobr>🟢</nobr> |
| **TPU** | <nobr>🟢</nobr> |
| **CPU** | <nobr>🟢 (x86) 🟡 (MacOS) </nobr> |
!!! note
More hardware platforms may be supported via plugins, e.g.:
- [vllm-ascend](https://github.com/vllm-project/vllm-ascend)
- [vllm-spyre](https://github.com/vllm-project/vllm-spyre)
- [vllm-openvino](https://github.com/vllm-project/vllm-openvino)
Please check their corresponding repositories for more details.
### Models
| Model Type | Status |
|-----------------------------|------------------------------------------------------------------------------------|
| **Decoder-only Models** | <nobr>🚀 Optimized</nobr> |
| **Encoder-Decoder Models** | <nobr>🟠 Delayed</nobr> |
| **Embedding Models** | <nobr>🟢 Functional</nobr> |
| **Mamba Models** | <nobr>🚧 WIP ([PR #19327](https://github.com/vllm-project/vllm/pull/19327))</nobr> |
| **Multimodal Models** | <nobr>🟢 Functional</nobr> |
vLLM V1 currently excludes model architectures with the `SupportsV0Only` protocol.
!!! tip
This corresponds to the V1 column in our [list of supported models][supported-models].
See below for the status of models that are not yet supported or have more features planned in V1.
#### Embedding Models
The initial basic support is now functional.
| Hardware | Status |
|----------|------------------------------------------|
| **NVIDIA** | <nobr>🚀 Natively Supported</nobr> |
| **AMD** | <nobr>🚧 WIP</nobr> |
| **TPU** | <nobr>🚧 WIP</nobr> |
| **CPU** | <nobr>🚧 WIP</nobr> |
Later, we will consider using [hidden states processor](https://github.com/vllm-project/vllm/issues/12249),
which is based on [global logits processor](https://github.com/vllm-project/vllm/pull/13360)
to enable simultaneous generation and embedding using the same engine instance in V1.
#### Feature / Model
#### Mamba Models
| Feature / Model | Status |
|-----------------|-----------------------------------------------------------------------------------|
| **Prefix Caching** | <nobr>🚀 Optimized</nobr> |
| **Chunked Prefill** | <nobr>🚀 Optimized</nobr> |
Models using selective state-space mechanisms instead of standard transformer attention (e.g., `MambaForCausalLM`, `JambaForCausalLM`)
will be supported via [PR #19327](https://github.com/vllm-project/vllm/pull/19327).
#### Encoder-Decoder Models
Models requiring cross-attention between separate encoder and decoder (e.g., `BartForConditionalGeneration`, `MllamaForConditionalGeneration`)
are not yet supported.
### Features
| Feature | Status |
|---------------------------------------------|-----------------------------------------------------------------------------------|
| **Prefix Caching** | <nobr>🚀 Optimized</nobr> |
| **Chunked Prefill** | <nobr>🚀 Optimized</nobr> |
| **LoRA** | <nobr>🚀 Optimized</nobr> |
| **Logprobs Calculation** | <nobr>🟢 Functional</nobr> |
| **Multimodal Models** | <nobr>🟢 Functional</nobr> |
| **FP8 KV Cache** | <nobr>🟢 Functional on Hopper devices ([PR #15191](https://github.com/vllm-project/vllm/pull/15191))</nobr>|
| **Spec Decode** | <nobr>🚧 WIP ([PR #13933](https://github.com/vllm-project/vllm/pull/13933))</nobr>|
| **Spec Decode** | <nobr>🚀 Optimized</nobr> |
| **Prompt Logprobs with Prefix Caching** | <nobr>🟡 Planned ([RFC #13414](https://github.com/vllm-project/vllm/issues/13414))</nobr>|
| **Structured Output Alternative Backends** | <nobr>🟡 Planned</nobr> |
| **Embedding Models** | <nobr>🚧 WIP ([PR #16188](https://github.com/vllm-project/vllm/pull/16188))</nobr> |
| **Mamba Models** | <nobr>🟡 Planned</nobr> |
| **Encoder-Decoder Models** | <nobr>🟠 Delayed</nobr> |
| **Structured Output Alternative Backends** | <nobr>🟢 Functional</nobr> |
| **Request-level Structured Output Backend** | <nobr>🔴 Deprecated</nobr> |
| **best_of** | <nobr>🔴 Deprecated ([RFC #13361](https://github.com/vllm-project/vllm/issues/13361))</nobr>|
| **Per-Request Logits Processors** | <nobr>🔴 Deprecated ([RFC #13360](https://github.com/vllm-project/vllm/pull/13360))</nobr> |
| **GPU <> CPU KV Cache Swapping** | <nobr>🔴 Deprecated</nobr> |
- **🚀 Optimized**: Nearly fully optimized, with no further work currently planned.
- **🟢 Functional**: Fully operational, with ongoing optimizations.
- **🚧 WIP**: Under active development.
- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
- **🟠 Delayed**: Temporarily dropped in V1 but planned to be re-introduced later.
- **🔴 Deprecated**: Not planned for V1 unless there is strong demand.
**Note**: vLLM V1’s unified scheduler treats both prompt and output tokens the same
way by using a simple dictionary (e.g., `{request_id: num_tokens}`) to dynamically
allocate a fixed token budget per request, enabling features like chunked prefills,
prefix caching, and speculative decoding without a strict separation between prefill
and decode phases.
!!! note
### Semantic Changes and Deprecated Features
vLLM V1’s unified scheduler treats both prompt and output tokens the same
way by using a simple dictionary (e.g., `{request_id: num_tokens}`) to dynamically
allocate a fixed token budget per request, enabling features like chunked prefills,
prefix caching, and speculative decoding without a strict separation between prefill
and decode phases.
#### Logprobs
#### Semantic Changes to Logprobs
vLLM V1 supports logprobs and prompt logprobs. However, there are some important semantic
differences compared to V0:
......@@ -115,46 +174,4 @@ to handle request preemptions.
**Structured Output features**
- **Request-level Structured Output Backend**: Deprecated, alternative backends
(outlines, guidance) with fallbacks is WIP.
### Feature & Model Support in Progress
Although we have re-implemented and partially optimized many features and models from V0 in vLLM V1, optimization work is still ongoing for some, and others remain unsupported.
#### Features to Be Optimized
These features are already supported in vLLM V1, but their optimization is still
in progress.
- **Spec Decode**: Currently, only ngram-based spec decode is supported in V1. There
will be follow-up work to support other types of spec decode (e.g., see [PR #13933](https://github.com/vllm-project/vllm/pull/13933)). We will prioritize the support for Eagle, MTP compared to draft model based spec decode.
- **Multimodal Models**: V1 is almost fully compatible with V0 except that interleaved modality input is not supported yet.
See [here](https://github.com/orgs/vllm-project/projects/8) for the status of upcoming features and optimizations.
#### Features to Be Supported
- **Structured Output Alternative Backends**: Structured output alternative backends (outlines, guidance) support is planned. V1 currently
supports only the `xgrammar:no_fallback` mode, meaning that it will error out if the output schema is unsupported by xgrammar.
Details about the structured outputs can be found
[here](https://docs.vllm.ai/en/latest/features/structured_outputs.html).
#### Models to Be Supported
vLLM V1 currently excludes model architectures with the `SupportsV0Only` protocol,
and the majority fall into the following categories. V1 support for these models will be added eventually.
**Embedding Models**
The initial support will be provided by [PR #16188](https://github.com/vllm-project/vllm/pull/16188).
Later, we will consider using [hidden states processor](https://github.com/vllm-project/vllm/issues/12249), which is based on [global logits processor](https://github.com/vllm-project/vllm/pull/13360) to enable simultaneous generation and embedding using the same engine instance in V1.
**Mamba Models**
Models using selective state-space mechanisms (instead of standard transformer attention)
are not yet supported (e.g., `MambaForCausalLM`, `JambaForCausalLM`).
**Encoder-Decoder Models**
vLLM V1 is currently optimized for decoder-only transformers. Models requiring
cross-attention between separate encoder and decoder are not yet supported (e.g., `BartForConditionalGeneration`, `MllamaForConditionalGeneration`).
For a complete list of supported models, see the [list of supported models](https://docs.vllm.ai/en/latest/models/supported_models.html).
- **Request-level Structured Output Backend**: Deprecated, alternative backends (outlines, guidance) with fallbacks is supported now.
examples/offline_inference/basic/README.md
View file @ 99324e25
......@@ -70,7 +70,7 @@ Try one yourself by passing one of the following models to the `--model` argumen
vLLM supports models that are quantized using GGUF.
Try one yourself by downloading a GUFF quantised model and using the following arguments:
Try one yourself by downloading a quantized GGUF model and using the following arguments:
```python
from huggingface_hub import hf_hub_download
......
examples/offline_inference/basic/embed.py
View file @ 99324e25
......@@ -12,7 +12,10 @@ def parse_args():
parser = EngineArgs.add_cli_args(parser)
# Set example specific arguments
parser.set_defaults(
model="intfloat/e5-mistral-7b-instruct", task="embed", enforce_eager=True
model="intfloat/e5-mistral-7b-instruct",
task="embed",
enforce_eager=True,
max_model_len=1024,
)
return parser.parse_args()
......
examples/offline_inference/data_parallel.py
View file @ 99324e25
......@@ -64,6 +64,18 @@ def parse_args():
parser.add_argument(
"--trust-remote-code", action="store_true", help="Trust remote code."
)
parser.add_argument(
"--max-num-seqs",
type=int,
default=64,
help=("Maximum number of sequences to be processed in a single iteration."),
)
parser.add_argument(
"--gpu-memory-utilization",
type=float,
default=0.8,
help=("Fraction of GPU memory vLLM is allowed to allocate (0.0, 1.0]."),
)
return parser.parse_args()
......@@ -77,6 +89,8 @@ def main(
GPUs_per_dp_rank,
enforce_eager,
trust_remote_code,
max_num_seqs,
gpu_memory_utilization,
):
os.environ["VLLM_DP_RANK"] = str(global_dp_rank)
os.environ["VLLM_DP_RANK_LOCAL"] = str(local_dp_rank)
......@@ -127,6 +141,8 @@ def main(
enforce_eager=enforce_eager,
enable_expert_parallel=True,
trust_remote_code=trust_remote_code,
max_num_seqs=max_num_seqs,
gpu_memory_utilization=gpu_memory_utilization,
)
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
......@@ -181,6 +197,8 @@ if __name__ == "__main__":
tp_size,
args.enforce_eager,
args.trust_remote_code,
args.max_num_seqs,
args.gpu_memory_utilization,
),
)
proc.start()
......
examples/offline_inference/mistral-small.py
View file @ 99324e25
......@@ -6,6 +6,7 @@ import argparse
from vllm import LLM
from vllm.sampling_params import SamplingParams
from vllm.assets.image import ImageAsset
# This script is an offline demo for running Mistral-Small-3.1
#
......@@ -71,14 +72,16 @@ def run_simple_demo(args: argparse.Namespace):
)
prompt = "Describe this image in one sentence."
image_url = "https://picsum.photos/id/237/200/300"
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": prompt},
{"type": "image_url", "image_url": {"url": image_url}},
{
"type": "image_pil",
"image_pil": ImageAsset("cherry_blossom").pil_image,
},
],
},
]
......
examples/offline_inference/openai_batch/README.md
View file @ 99324e25
......@@ -29,14 +29,14 @@ We currently support `/v1/chat/completions`, `/v1/embeddings`, and `/v1/score` e
To follow along with this example, you can download the example batch, or create your own batch file in your working directory.
```console
```bash
wget https://raw.githubusercontent.com/vllm-project/vllm/main/examples/offline_inference/openai_batch/openai_example_batch.jsonl
```
Once you've created your batch file it should look like this
```console
$ cat offline_inference/openai_batch/openai_example_batch.jsonl
```bash
cat offline_inference/openai_batch/openai_example_batch.jsonl
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_completion_tokens": 1000}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_completion_tokens": 1000}}
```
......@@ -47,7 +47,7 @@ The batch running tool is designed to be used from the command line.
You can run the batch with the following command, which will write its results to a file called `results.jsonl`
```console
```bash
python -m vllm.entrypoints.openai.run_batch \
-i offline_inference/openai_batch/openai_example_batch.jsonl \
-o results.jsonl \
......@@ -56,7 +56,7 @@ python -m vllm.entrypoints.openai.run_batch \
or use command-line:
```console
```bash
vllm run-batch \
-i offline_inference/openai_batch/openai_example_batch.jsonl \
-o results.jsonl \
......@@ -67,8 +67,8 @@ vllm run-batch \
You should now have your results at `results.jsonl`. You can check your results by running `cat results.jsonl`
```console
$ cat results.jsonl
```bash
cat results.jsonl
{"id":"vllm-383d1c59835645aeb2e07d004d62a826","custom_id":"request-1","response":{"id":"cmpl-61c020e54b964d5a98fa7527bfcdd378","object":"chat.completion","created":1715633336,"model":"meta-llama/Meta-Llama-3-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"Hello! It's great to meet you! I'm here to help with any questions or tasks you may have. What's on your mind today?"},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":25,"total_tokens":56,"completion_tokens":31}},"error":null}
{"id":"vllm-42e3d09b14b04568afa3f1797751a267","custom_id":"request-2","response":{"id":"cmpl-f44d049f6b3a42d4b2d7850bb1e31bcc","object":"chat.completion","created":1715633336,"model":"meta-llama/Meta-Llama-3-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"*silence*"},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":27,"total_tokens":32,"completion_tokens":5}},"error":null}
```
......@@ -79,7 +79,7 @@ The batch runner supports remote input and output urls that are accessible via h
For example, to run against our example input file located at `https://raw.githubusercontent.com/vllm-project/vllm/main/examples/offline_inference/openai_batch/openai_example_batch.jsonl`, you can run
```console
```bash
python -m vllm.entrypoints.openai.run_batch \
-i https://raw.githubusercontent.com/vllm-project/vllm/main/examples/offline_inference/openai_batch/openai_example_batch.jsonl \
-o results.jsonl \
......@@ -88,7 +88,7 @@ python -m vllm.entrypoints.openai.run_batch \
or use command-line:
```console
```bash
vllm run-batch \
-i https://raw.githubusercontent.com/vllm-project/vllm/main/examples/offline_inference/openai_batch/openai_example_batch.jsonl \
-o results.jsonl \
......@@ -112,21 +112,21 @@ To integrate with cloud blob storage, we recommend using presigned urls.
To follow along with this example, you can download the example batch, or create your own batch file in your working directory.
```console
```bash
wget https://raw.githubusercontent.com/vllm-project/vllm/main/examples/offline_inference/openai_batch/openai_example_batch.jsonl
```
Once you've created your batch file it should look like this
```console
$ cat offline_inference/openai_batch/openai_example_batch.jsonl
```bash
cat offline_inference/openai_batch/openai_example_batch.jsonl
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_completion_tokens": 1000}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_completion_tokens": 1000}}
```
Now upload your batch file to your S3 bucket.
```console
```bash
aws s3 cp offline_inference/openai_batch/openai_example_batch.jsonl s3://MY_BUCKET/MY_INPUT_FILE.jsonl
```
......@@ -181,7 +181,7 @@ output_url='https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_OUTPUT_FILE.jsonl?AW
You can now run the batch runner, using the urls generated in the previous section.
```console
```bash
python -m vllm.entrypoints.openai.run_batch \
-i "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_INPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
-o "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_OUTPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
......@@ -190,7 +190,7 @@ python -m vllm.entrypoints.openai.run_batch \
or use command-line:
```console
```bash
vllm run-batch \
-i "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_INPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
-o "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_OUTPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
......@@ -201,7 +201,7 @@ vllm run-batch \
Your results are now on S3. You can view them in your terminal by running
```console
```bash
aws s3 cp s3://MY_BUCKET/MY_OUTPUT_FILE.jsonl -
```
......@@ -230,8 +230,8 @@ You can run the batch using the same command as in earlier examples.
You can check your results by running `cat results.jsonl`
```console
$ cat results.jsonl
```bash
cat results.jsonl
{"id":"vllm-db0f71f7dec244e6bce530e0b4ef908b","custom_id":"request-1","response":{"status_code":200,"request_id":"vllm-batch-3580bf4d4ae54d52b67eee266a6eab20","body":{"id":"embd-33ac2efa7996430184461f2e38529746","object":"list","created":444647,"model":"intfloat/e5-mistral-7b-instruct","data":[{"index":0,"object":"embedding","embedding":[0.016204833984375,0.0092010498046875,0.0018358230590820312,-0.0028228759765625,0.001422882080078125,-0.0031147003173828125,...]}],"usage":{"prompt_tokens":8,"total_tokens":8,"completion_tokens":0}}},"error":null}
...
```
......@@ -261,8 +261,8 @@ You can run the batch using the same command as in earlier examples.
You can check your results by running `cat results.jsonl`
```console
$ cat results.jsonl
```bash
cat results.jsonl
{"id":"vllm-f87c5c4539184f618e555744a2965987","custom_id":"request-1","response":{"status_code":200,"request_id":"vllm-batch-806ab64512e44071b37d3f7ccd291413","body":{"id":"score-4ee45236897b4d29907d49b01298cdb1","object":"list","created":1737847944,"model":"BAAI/bge-reranker-v2-m3","data":[{"index":0,"object":"score","score":0.0010900497436523438},{"index":1,"object":"score","score":1.0}],"usage":{"prompt_tokens":37,"total_tokens":37,"completion_tokens":0,"prompt_tokens_details":null}}},"error":null}
{"id":"vllm-41990c51a26d4fac8419077f12871099","custom_id":"request-2","response":{"status_code":200,"request_id":"vllm-batch-73ce66379026482699f81974e14e1e99","body":{"id":"score-13f2ffe6ba40460fbf9f7f00ad667d75","object":"list","created":1737847944,"model":"BAAI/bge-reranker-v2-m3","data":[{"index":0,"object":"score","score":0.001094818115234375},{"index":1,"object":"score","score":1.0}],"usage":{"prompt_tokens":37,"total_tokens":37,"completion_tokens":0,"prompt_tokens_details":null}}},"error":null}
```
examples/offline_inference/profiling_tpu/README.md
View file @ 99324e25
......@@ -4,7 +4,7 @@ This script is used to profile the TPU performance of vLLM for specific prefill
Note: an actual running server is a mix of both prefill of many shapes and decode of many shapes.
We assume you are on a TPU already (this was tested on TPU v6e) and have installed vLLM according to the [installation guide](https://docs.vllm.ai/en/latest/getting_started/installation/ai_accelerator/index.html).
We assume you are on a TPU already (this was tested on TPU v6e) and have installed vLLM according to the [Google TPU installation guide](https://docs.vllm.ai/en/latest/getting_started/installation/google_tpu.html).
> In all examples below, we run several warmups before (so `--enforce-eager` is okay)
......@@ -57,7 +57,10 @@ Once you have collected your profiles with this script, you can visualize them u
Here are most likely the dependencies you need to install:
```bash
pip install tensorflow-cpu tensorboard-plugin-profile etils importlib_resources
pip install tensorflow-cpu \
tensorboard-plugin-profile \
etils \
importlib_resources
```
Then you just need to point TensorBoard to the directory where you saved the profiles and visit `http://localhost:6006/` in your browser:
......
examples/offline_inference/qwen3_reranker.py 0 → 100644
View file @ 99324e25
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# ruff: noqa: E501
from vllm import LLM
model_name = "Qwen/Qwen3-Reranker-0.6B"
# What is the difference between the official original version and one
# that has been converted into a sequence classification model?
# Qwen3-Reranker is a language model that doing reranker by using the
# logits of "no" and "yes" tokens.
# It needs to computing 151669 tokens logits, making this method extremely
# inefficient, not to mention incompatible with the vllm score API.
# A method for converting the original model into a sequence classification
# model was proposed. See：https://huggingface.co/Qwen/Qwen3-Reranker-0.6B/discussions/3
# Models converted offline using this method can not only be more efficient
# and support the vllm score API, but also make the init parameters more
# concise, for example.
# model = LLM(model="tomaarsen/Qwen3-Reranker-0.6B-seq-cls", task="score")
# If you want to load the official original version, the init parameters are
# as follows.
def get_model() -> LLM:
"""Initializes and returns the LLM model for Qwen3-Reranker."""
return LLM(
model=model_name,
task="score",
hf_overrides={
"architectures": ["Qwen3ForSequenceClassification"],
"classifier_from_token": ["no", "yes"],
"is_original_qwen3_reranker": True,
},
)
# Why do we need hf_overrides for the official original version:
# vllm converts it to Qwen3ForSequenceClassification when loaded for
# better performance.
# - Firstly, we need using `"architectures": ["Qwen3ForSequenceClassification"],`
# to manually route to Qwen3ForSequenceClassification.
# - Then, we will extract the vector corresponding to classifier_from_token
# from lm_head using `"classifier_from_token": ["no", "yes"]`.
# - Third, we will convert these two vectors into one vector. The use of
# conversion logic is controlled by `using "is_original_qwen3_reranker": True`.
# Please use the query_template and document_template to format the query and
# document for better reranker results.
prefix = '<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n'
suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
query_template = "{prefix}<Instruct>: {instruction}\n<Query>: {query}\n"
document_template = "<Document>: {doc}{suffix}"
def main() -> None:
instruction = (
"Given a web search query, retrieve relevant passages that answer the query"
)
queries = [
"What is the capital of China?",
"Explain gravity",
]
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]
queries = [
query_template.format(prefix=prefix, instruction=instruction, query=query)
for query in queries
]
documents = [document_template.format(doc=doc, suffix=suffix) for doc in documents]
model = get_model()
outputs = model.score(queries, documents)
print("-" * 30)
print([output.outputs.score for output in outputs])
print("-" * 30)
if __name__ == "__main__":
main()
examples/offline_inference/eagle.py → examples/offline_inference/spec_decode.py
View file @ 99324e25
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
import json
import os
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
from vllm.benchmarks.datasets import add_dataset_parser, get_samples
from vllm.v1.metrics.reader import Counter, Vector
def load_prompts(dataset_path, num_prompts):
if os.path.exists(dataset_path):
prompts = []
try:
with open(dataset_path) as f:
for line in f:
data = json.loads(line)
prompts.append(data["turns"][0])
except Exception as e:
print(f"Error reading dataset: {e}")
return []
else:
prompts = ["The future of AI is", "The president of the United States is"]
return prompts[:num_prompts]
try:
from vllm.utils import FlexibleArgumentParser
except ImportError:
from argparse import ArgumentParser as FlexibleArgumentParser
def parse_args():
parser = argparse.ArgumentParser()
parser = FlexibleArgumentParser()
add_dataset_parser(parser)
parser.add_argument(
"--dataset",
"--method",
type=str,
default="./examples/data/gsm8k.jsonl",
help="downloaded from the eagle repo "
"https://github.com/SafeAILab/EAGLE/blob/main/eagle/data/",
default="eagle",
choices=["ngram", "eagle", "eagle3", "mtp"],
)
parser.add_argument(
"--method", type=str, default="eagle", choices=["eagle", "eagle3"]
)
parser.add_argument("--max_num_seqs", type=int, default=8)
parser.add_argument("--num_prompts", type=int, default=80)
parser.add_argument("--num_spec_tokens", type=int, default=2)
parser.add_argument("--num-spec-tokens", type=int, default=2)
parser.add_argument("--prompt-lookup-max", type=int, default=5)
parser.add_argument("--prompt-lookup-min", type=int, default=2)
parser.add_argument("--tp", type=int, default=1)
parser.add_argument("--draft_tp", type=int, default=1)
parser.add_argument("--enforce_eager", action="store_true")
parser.add_argument("--enable_chunked_prefill", action="store_true")
parser.add_argument("--max_num_batched_tokens", type=int, default=2048)
parser.add_argument("--enforce-eager", action="store_true")
parser.add_argument("--enable-chunked-prefill", action="store_true")
parser.add_argument("--temp", type=float, default=0)
parser.add_argument("--top-p", type=float, default=1.0)
parser.add_argument("--top-k", type=int, default=-1)
parser.add_argument("--print-output", action="store_true")
parser.add_argument("--output-len", type=int, default=256)
parser.add_argument("--model-dir", type=str, default=None)
parser.add_argument("--eagle-dir", type=str, default=None)
return parser.parse_args()
def main():
args = parse_args()
args.endpoint_type = "openai-chat"
model_dir = "meta-llama/Llama-3.1-8B-Instruct"
if args.method == "eagle":
eagle_dir = "yuhuili/EAGLE-LLaMA3.1-Instruct-8B"
elif args.method == "eagle3":
eagle_dir = "yuhuili/EAGLE3-LLaMA3.1-Instruct-8B"
else:
raise ValueError(f"unknown method: {args.method}")
max_model_len = 2048
model_dir = args.model_dir
if args.model_dir is None:
model_dir = "meta-llama/Llama-3.1-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_dir)
prompts = load_prompts(args.dataset, args.num_prompts)
prompts = get_samples(args, tokenizer)
# add_special_tokens is False to avoid adding bos twice when using chat templates
prompt_ids = [
tokenizer.apply_chat_template(
[{"role": "user", "content": prompt}], add_generation_prompt=True
)
for prompt in prompts
tokenizer.encode(prompt.prompt, add_special_tokens=False) for prompt in prompts
]
if args.method == "eagle" or args.method == "eagle3":
eagle_dir = args.eagle_dir
if args.method == "eagle" and eagle_dir is None:
eagle_dir = "yuhuili/EAGLE-LLaMA3.1-Instruct-8B"
elif args.method == "eagle3" and eagle_dir is None:
eagle_dir = "yuhuili/EAGLE3-LLaMA3.1-Instruct-8B"
speculative_config = {
"method": args.method,
"model": eagle_dir,
"num_speculative_tokens": args.num_spec_tokens,
}
elif args.method == "ngram":
speculative_config = {
"method": "ngram",
"num_speculative_tokens": args.num_spec_tokens,
"prompt_lookup_max": args.prompt_lookup_max,
"prompt_lookup_min": args.prompt_lookup_min,
}
else:
raise ValueError(f"unknown method: {args.method}")
llm = LLM(
model=model_dir,
trust_remote_code=True,
tensor_parallel_size=args.tp,
enable_chunked_prefill=args.enable_chunked_prefill,
max_num_batched_tokens=args.max_num_batched_tokens,
enforce_eager=args.enforce_eager,
max_model_len=max_model_len,
max_num_seqs=args.max_num_seqs,
gpu_memory_utilization=0.8,
speculative_config={
"method": args.method,
"model": eagle_dir,
"num_speculative_tokens": args.num_spec_tokens,
"draft_tensor_parallel_size": args.draft_tp,
"max_model_len": max_model_len,
},
speculative_config=speculative_config,
disable_log_stats=False,
)
sampling_params = SamplingParams(temperature=args.temp, max_tokens=256)
sampling_params = SamplingParams(temperature=args.temp, max_tokens=args.output_len)
outputs = llm.generate(prompt_token_ids=prompt_ids, sampling_params=sampling_params)
# print the generated text
for output in outputs:
print("-" * 50)
print(f"prompt: {output.prompt}")
print(f"generated text: {output.outputs[0].text}")
print("-" * 50)
if args.print_output:
for output in outputs:
print("-" * 50)
print(f"prompt: {output.prompt}")
print(f"generated text: {output.outputs[0].text}")
print("-" * 50)
try:
metrics = llm.get_metrics()
......@@ -113,27 +103,41 @@ def main():
print("Metrics are not supported in the V0 engine.")
return
num_drafts = num_accepted = 0
total_num_output_tokens = sum(
len(output.outputs[0].token_ids) for output in outputs
)
num_drafts = 0
num_draft_tokens = 0
num_accepted_tokens = 0
acceptance_counts = [0] * args.num_spec_tokens
for metric in metrics:
if metric.name == "vllm:spec_decode_num_drafts":
assert isinstance(metric, Counter)
num_drafts += metric.value
elif metric.name == "vllm:spec_decode_num_draft_tokens":
assert isinstance(metric, Counter)
num_draft_tokens += metric.value
elif metric.name == "vllm:spec_decode_num_accepted_tokens":
assert isinstance(metric, Counter)
num_accepted += metric.value
num_accepted_tokens += metric.value
elif metric.name == "vllm:spec_decode_num_accepted_tokens_per_pos":
assert isinstance(metric, Vector)
for pos in range(len(metric.values)):
acceptance_counts[pos] += metric.values[pos]
print("-" * 50)
print(f"mean acceptance length: {1 + (num_accepted / num_drafts):.2f}")
print(f"total_num_output_tokens: {total_num_output_tokens}")
print(f"num_drafts: {num_drafts}")
print(f"num_draft_tokens: {num_draft_tokens}")
print(f"num_accepted_tokens: {num_accepted_tokens}")
acceptance_length = 1 + (num_accepted_tokens / num_drafts) if num_drafts > 0 else 1
print(f"mean acceptance length: {acceptance_length:.2f}")
print("-" * 50)
# print acceptance at each token position
for i in range(len(acceptance_counts)):
print(f"acceptance at token {i}:{acceptance_counts[i] / num_drafts:.2f}")
acceptance_rate = acceptance_counts[i] / num_drafts if num_drafts > 0 else 0
print(f"acceptance at token {i}: {acceptance_rate:.2f}")
if __name__ == "__main__":
......
examples/offline_inference/vision_language.py
View file @ 99324e25
......@@ -98,7 +98,7 @@ def run_blip2(questions: list[str], modality: str) -> ModelRequestData:
# See https://huggingface.co/Salesforce/blip2-opt-2.7b/discussions/15#64ff02f3f8cf9e4f5b038262 #noqa
prompts = [f"Question: {question} Answer:" for question in questions]
engine_args = EngineArgs(
model="Salesforce/blip2-opt-6.7b",
model="Salesforce/blip2-opt-2.7b",
limit_mm_per_prompt={modality: 1},
)
......@@ -248,6 +248,42 @@ def run_glm4v(questions: list[str], modality: str) -> ModelRequestData:
)
# GLM-4.1V
def run_glm4_1v(questions: list[str], modality: str) -> ModelRequestData:
model_name = "THUDM/GLM-4.1V-9B-Thinking"
engine_args = EngineArgs(
model=model_name,
max_model_len=4096,
max_num_seqs=2,
mm_processor_kwargs={
"size": {"shortest_edge": 12544, "longest_edge": 47040000},
"fps": 1,
},
limit_mm_per_prompt={modality: 1},
enforce_eager=True,
)
if modality == "image":
placeholder = "<|begin_of_image|><|image|><|end_of_image|>"
elif modality == "video":
placeholder = "<|begin_of_video|><|video|><|end_of_video|>"
prompts = [
(
"[gMASK]<sop><|system|>\nYou are a helpful assistant.<|user|>\n"
f"{placeholder}"
f"{question}<|assistant|>assistant\n"
)
for question in questions
]
return ModelRequestData(
engine_args=engine_args,
prompts=prompts,
)
# H2OVL-Mississippi
def run_h2ovl(questions: list[str], modality: str) -> ModelRequestData:
assert modality == "image"
......@@ -393,6 +429,37 @@ def run_internvl(questions: list[str], modality: str) -> ModelRequestData:
)
# Keye-VL
def run_keye_vl(questions: list[str], modality: str) -> ModelRequestData:
model_name = "Kwai-Keye/Keye-VL-8B-Preview"
engine_args = EngineArgs(
model=model_name,
max_model_len=8192,
trust_remote_code=True,
limit_mm_per_prompt={modality: 1},
)
if modality == "image":
placeholder = "<|image_pad|>"
elif modality == "video":
placeholder = "<|video_pad|>"
prompts = [
(
f"<|im_start|>user\n<|vision_start|>{placeholder}<|vision_end|>"
f"{question}<|im_end|>\n"
"<|im_start|>assistant\n"
)
for question in questions
]
return ModelRequestData(
engine_args=engine_args,
prompts=prompts,
)
# Kimi-VL
def run_kimi_vl(questions: list[str], modality: str) -> ModelRequestData:
assert modality == "image"
......@@ -610,6 +677,7 @@ def run_mistral3(questions: list[str], modality: str) -> ModelRequestData:
max_num_seqs=2,
tensor_parallel_size=2,
limit_mm_per_prompt={modality: 1},
ignore_patterns=["consolidated.safetensors"],
)
prompts = [f"<s>[INST]{question}\n[IMG][/INST]" for question in questions]
......@@ -903,7 +971,7 @@ def run_pixtral_hf(questions: list[str], modality: str) -> ModelRequestData:
)
# Qwen
# Qwen-VL
def run_qwen_vl(questions: list[str], modality: str) -> ModelRequestData:
assert modality == "image"
......@@ -1040,6 +1108,37 @@ def run_qwen2_5_omni(questions: list[str], modality: str):
)
def run_tarsier2(questions: list[str], modality: str) -> ModelRequestData:
model_name = "omni-research/Tarsier2-Recap-7b"
engine_args = EngineArgs(
model=model_name,
max_model_len=4096,
hf_overrides={"architectures": ["Tarsier2ForConditionalGeneration"]},
limit_mm_per_prompt={modality: 1},
)
if modality == "image":
placeholder = "<|image_pad|>"
elif modality == "video":
placeholder = "<|video_pad|>"
prompts = [
(
"<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"
f"<|im_start|>user\n<|vision_start|>{placeholder}<|vision_end|>"
f"{question}<|im_end|>\n"
"<|im_start|>assistant\n"
)
for question in questions
]
return ModelRequestData(
engine_args=engine_args,
prompts=prompts,
)
# SkyworkR1V
def run_skyworkr1v(questions: list[str], modality: str) -> ModelRequestData:
assert modality == "image"
......@@ -1083,9 +1182,11 @@ model_example_map = {
"fuyu": run_fuyu,
"gemma3": run_gemma3,
"glm4v": run_glm4v,
"glm4_1v": run_glm4_1v,
"h2ovl_chat": run_h2ovl,
"idefics3": run_idefics3,
"internvl_chat": run_internvl,
"keye_vl": run_keye_vl,
"kimi_vl": run_kimi_vl,
"llava": run_llava,
"llava-next": run_llava_next,
......@@ -1112,6 +1213,7 @@ model_example_map = {
"skywork_chat": run_skyworkr1v,
"smolvlm": run_smolvlm,
"tarsier": run_tarsier,
"tarsier2": run_tarsier2,
}
......@@ -1140,10 +1242,11 @@ def get_multi_modal_input(args):
if args.modality == "video":
# Input video and question
video = VideoAsset(name="baby_reading", num_frames=args.num_frames).np_ndarrays
metadata = VideoAsset(name="baby_reading", num_frames=args.num_frames).metadata
vid_questions = ["Why is this video funny?"]
return {
"data": video,
"data": [(video, metadata)] if args.model_type == "glm4_1v" else video,
"questions": vid_questions,
}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment