The `seed` parameter in vLLM is used to control the random states for various random number generators. This parameter can affect the behavior of random operations in user code, especially when working with models in vLLM.
## Default Behavior
By default, the `seed` parameter is set to `None`. When the `seed` parameter is `None`, the global random states for `random`, `np.random`, and `torch.manual_seed` are not set. This means that the random operations will behave as expected, without any fixed random states.
## Specifying a Seed
If a specific seed value is provided, the global random states for `random`, `np.random`, and `torch.manual_seed` will be set accordingly. This can be useful for reproducibility, as it ensures that the random operations produce the same results across multiple runs.
## Example Usage
### Without Specifying a Seed
```python
importrandom
fromvllmimportLLM
# Initialize a vLLM model without specifying a seed
model=LLM(model="Qwen/Qwen2.5-0.5B-Instruct")
# Try generating random numbers
print(random.randint(0,100))# Outputs different numbers across runs
print(random.randint(0,100))# Outputs the same number across runs
```
## Important Notes
- If the `seed` parameter is not specified, the behavior of global random states remains unaffected.
- If a specific seed value is provided, the global random states for `random`, `np.random`, and `torch.manual_seed` will be set to that value.
- This behavior can be useful for reproducibility but may lead to non-intuitive behavior if the user is not explicitly aware of it.
## Conclusion
Understanding the behavior of the `seed` parameter in vLLM is crucial for ensuring the expected behavior of random operations in your code. By default, the `seed` parameter is set to `None`, which means that the global random states are not affected. However, specifying a seed value can help achieve reproducibility in your experiments.
## How to decide the distributed inference strategy?
...
...
@@ -14,9 +15,8 @@ In short, you should increase the number of GPUs and the number of nodes until y
After adding enough GPUs and nodes to hold the model, you can run vLLM first, which will print some logs like `# GPU blocks: 790`. Multiply the number by `16` (the block size), and you can get roughly the maximum number of tokens that can be served on the current configuration. If this number is not satisfying, e.g. you want higher throughput, you can further increase the number of GPUs or nodes, until the number of blocks is enough.
:::{note}
There is one edge case: if the model fits in a single node with multiple GPUs, but the number of GPUs cannot divide the model size evenly, you can use pipeline parallelism, which splits the model along layers and supports uneven splits. In this case, the tensor parallel size should be 1 and the pipeline parallel size should be the number of GPUs.
:::
!!! note
There is one edge case: if the model fits in a single node with multiple GPUs, but the number of GPUs cannot divide the model size evenly, you can use pipeline parallelism, which splits the model along layers and supports uneven splits. In this case, the tensor parallel size should be 1 and the pipeline parallel size should be the number of GPUs.
## Running vLLM on a single node
...
...
@@ -77,13 +77,11 @@ bash run_cluster.sh \
Then you get a ray cluster of **containers**. Note that you need to keep the shells running these commands alive to hold the cluster. Any shell disconnect will terminate the cluster. In addition, please note that the argument `ip_of_head_node` should be the IP address of the head node, which is accessible by all the worker nodes. The IP addresses of each worker node should be specified in the `VLLM_HOST_IP` environment variable, and should be different for each worker node. Please check the network configuration of your cluster to make sure the nodes can communicate with each other through the specified IP addresses.
:::{warning}
It is considered best practice to set `VLLM_HOST_IP` to an address on a private network segment for the vLLM cluster. The traffic sent here is not encrypted. The endpoints are also exchanging data in a format that could be exploited to execute arbitrary code should a malicious party gain access to the network. Please ensure that this network is not reachable by any untrusted parties.
:::
!!! warning
It is considered best practice to set `VLLM_HOST_IP` to an address on a private network segment for the vLLM cluster. The traffic sent here is not encrypted. The endpoints are also exchanging data in a format that could be exploited to execute arbitrary code should a malicious party gain access to the network. Please ensure that this network is not reachable by any untrusted parties.
:::{warning}
Since this is a ray cluster of **containers**, all the following commands should be executed in the **containers**, otherwise you are executing the commands on the host machine, which is not connected to the ray cluster. To enter the container, you can use `docker exec -it node /bin/bash`.
:::
!!! warning
Since this is a ray cluster of **containers**, all the following commands should be executed in the **containers**, otherwise you are executing the commands on the host machine, which is not connected to the ray cluster. To enter the container, you can use `docker exec -it node /bin/bash`.
Then, on any node, use `docker exec -it node /bin/bash` to enter the container, execute `ray status` and `ray list nodes` to check the status of the Ray cluster. You should see the right number of nodes and GPUs.
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.
:::{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.
:::
!!! 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.
:::{warning}
Please make sure you downloaded the model to all the nodes (with the same path), or the model is downloaded to some distributed file system that is accessible by all nodes.
!!! warning
Please make sure you downloaded the model to all the nodes (with the same path), or the model is downloaded to some distributed file system that is accessible by all nodes.
When you use huggingface repo id to refer to the model, you should append your huggingface token to the `run_cluster.sh` script, e.g. `-e HF_TOKEN=`. The recommended way is to download the model first, and then use the path to refer to the model.
:::
When you use huggingface repo id to refer to the model, you should append your huggingface token to the `run_cluster.sh` script, e.g. `-e HF_TOKEN=`. The recommended way is to download the model first, and then use the path to refer to the model.
:::{warning}
If you keep receiving the error message `Error: No available node types can fulfill resource request` but you have enough GPUs in the cluster, chances are your nodes have multiple IP addresses and vLLM cannot find the right one, especially when you are using multi-node inference. Please make sure vLLM and ray use the same IP address. You can set the `VLLM_HOST_IP` environment variable to the right IP address in the `run_cluster.sh` script (different for each node!), and check `ray status` and `ray list nodes` to see the IP address used by Ray. See <gh-issue:7815> for more information.
:::
!!! warning
If you keep receiving the error message `Error: No available node types can fulfill resource request` but you have enough GPUs in the cluster, chances are your nodes have multiple IP addresses and vLLM cannot find the right one, especially when you are using multi-node inference. Please make sure vLLM and ray use the same IP address. You can set the `VLLM_HOST_IP` environment variable to the right IP address in the `run_cluster.sh` script (different for each node!), and check `ray status` and `ray list nodes` to see the IP address used by Ray. See <gh-issue:7815> for more information.
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.
In your terminal, you can [install](../getting_started/installation.md) vLLM, then start the server with the [`vllm serve`](#serve-args) command. (You can also use our [Docker](#deployment-docker) image.)
In your terminal, you can [install](../getting_started/installation/README.md) vLLM, then start the server with the [`vllm serve`][serve-args] command. (You can also use our [Docker][deployment-docker] image.)
```bash
vllm serve NousResearch/Meta-Llama-3-8B-Instruct --dtype auto --api-key token-abc123
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).
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`.
:::
!!! 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`.
:::{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.
!!! warning
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.
:::
To disable this behavior, please pass `--generation-config vllm` when launching the server.
@@ -387,17 +363,17 @@ It consists of two endpoints:
-`/tokenize` corresponds to calling `tokenizer.encode()`.
-`/detokenize` corresponds to calling `tokenizer.decode()`.
(pooling-api)=
[](){ #pooling-api }
### Pooling API
Our Pooling API encodes input prompts using a [pooling model](../models/pooling_models.md) and returns the corresponding hidden states.
The input format is the same as [Embeddings API](#embeddings-api), but the output data can contain an arbitrary nested list, not just a 1-D list of floats.
The input format is the same as [Embeddings API][embeddings-api], but the output data can contain an arbitrary nested list, not just a 1-D list of floats.
<p>You are viewing the latest developer preview docs. <ahref="https://docs.vllm.ai/en/stable/">Click here</a> to view docs for the latest stable release.</p>
This document walks you through the steps to extend a basic model so that it accepts [multi-modal inputs](#multimodal-inputs).
## 1. Update the base vLLM model
It is assumed that you have already implemented the model in vLLM according to [these steps](#new-model-basic).
Further update the model as follows:
- Reserve a keyword parameter in {meth}`~torch.nn.Module.forward` for each input tensor that corresponds to a multi-modal input, as shown in the following example:
```diff
def forward(
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
+ pixel_values: torch.Tensor,
) -> SamplerOutput:
```
More conveniently, you can simply pass `**kwargs` to the {meth}`~torch.nn.Module.forward` method and retrieve the keyword parameters for multimodal inputs from it.
- Implement {meth}`~vllm.model_executor.models.interfaces.SupportsMultiModal.get_multimodal_embeddings` that returns the embeddings from running the multimodal inputs through the multimodal tokenizer of the model. Below we provide a boilerplate of a typical implementation pattern, but feel free to adjust it to your own needs.
The returned `multimodal_embeddings` must be either a **3D {class}`torch.Tensor`** of shape `(num_items, feature_size, hidden_size)`, or a **list / tuple of 2D {class}`torch.Tensor`'s** of shape `(feature_size, hidden_size)`, so that `multimodal_embeddings[i]` retrieves the embeddings generated from the `i`-th multimodal data item (e.g, image) of the request.
:::
- Implement {meth}`~vllm.model_executor.models.interfaces.SupportsMultiModal.get_input_embeddings` to merge `multimodal_embeddings` with text embeddings from the `input_ids`. If input processing for the model is implemented correctly (see sections below), then you can leverage the utility function we provide to easily merge the embeddings.
- Implement {meth}`~vllm.model_executor.models.interfaces.SupportsMultiModal.get_language_model` getter to provide stable access to the underlying language model.
```python
class YourModelForImage2Seq(nn.Module):
...
def get_language_model(self) -> torch.nn.Module:
# Change `language_model` according to your implementation.
return self.language_model
```
- Once the above steps are done, update the model class with the {class}`~vllm.model_executor.models.interfaces.SupportsMultiModal` interface.
```diff
+ from vllm.model_executor.models.interfaces import SupportsMultiModal
- class YourModelForImage2Seq(nn.Module):
+ class YourModelForImage2Seq(nn.Module, SupportsMultiModal):
```
:::{note}
The model class does not have to be named {code}`*ForCausalLM`.
Check out [the HuggingFace Transformers documentation](https://huggingface.co/docs/transformers/model_doc/auto#multimodal) for some examples.
:::
## 2. Specify processing information
Next, create a subclass of {class}`~vllm.multimodal.processing.BaseProcessingInfo`
to provide basic information related to HF processing.
### Maximum number of input items
You need to override the abstract method {meth}`~vllm.multimodal.processing.BaseProcessingInfo.get_supported_mm_limits`
to return the maximum number of input items for each modality supported by the model.
For example, if the model supports any number of images but only one video per prompt:
Then, inherit {class}`~vllm.multimodal.profiling.BaseDummyInputsBuilder` to construct dummy inputs for
HF processing as well as memory profiling.
### For memory profiling
Override the abstract methods {meth}`~vllm.multimodal.profiling.BaseDummyInputsBuilder.get_dummy_text` and {meth}`~vllm.multimodal.profiling.BaseDummyInputsBuilder.get_dummy_mm_data` to construct dummy inputs for memory profiling. These dummy inputs should result in the worst-case memory usage of the model so that vLLM can reserve the correct amount of memory for it.
Assuming that the memory usage increases with the number of tokens, the dummy inputs can be constructed to maximize the number of output embeddings, which is the same number as placeholder feature tokens.
::::{tab-set}
:::{tab-item} Basic example: LLaVA
:sync: llava
Looking at the code of HF's `LlavaForConditionalGeneration`:
These image patches correspond to placeholder tokens (`|SPEAKER|`). So, we just need to maximize the number of image patches. Since input images are first resized
to fit within `image_processor.size`, we can maximize the number of image patches by inputting an image with size equal to `image_processor.size`.
class YourModelForImage2Seq(nn.Module, SupportsMultiModal):
```
## Notes
### Inserting feature tokens without replacement
Some HF processors directly insert feature tokens without replacing anything in the original prompt. In that case, you can use {class}`~vllm.multimodal.processing.PromptInsertion` instead of {class}`~vllm.multimodal.processing.PromptReplacement` inside {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates`.
Examples:
- BLIP-2 (insert at start of prompt): <gh-file:vllm/model_executor/models/blip2.py>
- Florence2 (insert at start of prompt): <gh-file:vllm/model_executor/models/florence2.py>
- Molmo (insert after `<|endoftext|>` token): <gh-file:vllm/model_executor/models/molmo.py>
### Handling prompt updates unrelated to multi-modal data
{meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates` assumes that each application of prompt update corresponds to one multi-modal item. If the HF processor performs additional processing regardless of how many multi-modal items there are, you should override {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._apply_hf_processor_tokens_only` so that the processed token inputs are consistent with the result of applying the HF processor on text inputs. This is because token inputs bypass the HF processor according to [our design](#mm-processing).
- Molmo (applies chat template which is not defined elsewhere): <gh-file:vllm/model_executor/models/molmo.py>
### Custom HF processor
Some models don't define a HF processor class on HF Hub. In that case, you can define a custom HF processor that has the same call signature as HF processors and pass it to {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._call_hf_processor`.
Helm is a package manager for Kubernetes. It will help you to deploy vLLM on k8s and automate the deployment of vLLM Kubernetes applications. With Helm, you can deploy the same framework architecture with different configurations to multiple namespaces by overriding variable values.
This guide will walk you through the process of deploying vLLM with Helm, including the necessary prerequisites, steps for helm installation and documentation on architecture and values file.
## Prerequisites
Before you begin, ensure that you have the following:
- A running Kubernetes cluster
- NVIDIA Kubernetes Device Plugin (`k8s-device-plugin`): This can be found at [https://github.com/NVIDIA/k8s-device-plugin](https://github.com/NVIDIA/k8s-device-plugin)
- Available GPU resources in your cluster
- S3 with the model which will be deployed
## Installing the chart
To install the chart with the release name `test-vllm`:
