Merge branch 'v0.6.3.post1-dev'

docs/source/serving/deploying_with_kserve.rst

@@ -5,4 +5,4 @@ Deploying with KServe
 
 vLLM can be deployed with `KServe <https://github.com/kserve/kserve>`_ on Kubernetes for highly scalable distributed model serving.
 
-Please see `this guide <https://kserve.github.io/website/latest/modelserving/v1beta1/llm/vllm/>`_ for more details on using vLLM with KServe.
+Please see `this guide <https://kserve.github.io/website/latest/modelserving/v1beta1/llm/huggingface/>`_ for more details on using vLLM with KServe.

docs/source/serving/faq.rst

@@ -10,3 +10,22 @@ A: Assuming that you're referring to using OpenAI compatible server to serve mul
     Q: Which model to use for offline inference embedding?
 
 A: If you want to use an embedding model, try: https://huggingface.co/intfloat/e5-mistral-7b-instruct. Instead models, such as Llama-3-8b, Mistral-7B-Instruct-v0.3, are generation models rather than an embedding model
+
+----------------------------------------
+
+    Q: Can the output of a prompt vary across runs in vLLM?
+
+A: Yes, it can. vLLM does not guarantee stable log probabilities (logprobs) for the output tokens. Variations in logprobs may occur due to
+numerical instability in Torch operations or non-deterministic behavior in batched Torch operations when batching changes. For more details, 
+see the `Numerical Accuracy section <https://pytorch.org/docs/stable/notes/numerical_accuracy.html#batched-computations-or-slice-computations>`_.
+
+In vLLM, the same requests might be batched differently due to factors such as other concurrent requests,
+changes in batch size, or batch expansion in speculative decoding. These batching variations, combined with numerical instability of Torch operations, 
+can lead to slightly different logit/logprob values at each step. Such differences can accumulate, potentially resulting in 
+different tokens being sampled. Once a different token is sampled, further divergence is likely.
+
+**Mitigation Strategies**
+
+- For improved stability and reduced variance, use `float32`. Note that this will require more memory.
+- If using `bfloat16`, switching to `float16` can also help.
+- Using request seeds can aid in achieving more stable generation for temperature > 0, but discrepancies due to precision differences may still occur.

docs/source/serving/integrations.rst

@@ -12,3 +12,4 @@ Integrations
    deploying_with_lws
    deploying_with_dstack
    serving_with_langchain
+   serving_with_llamaindex

docs/source/serving/openai_compatible_server.md

@@ -110,14 +110,182 @@ directory [here](https://github.com/vllm-project/vllm/tree/main/examples/)
 :func: create_parser_for_docs
 :prog: vllm serve
 ```
+## Tool Calling in the Chat Completion API
+### Named Function Calling
+vLLM supports only named function calling in the chat completion API by default. It does so using Outlines, so this is 
+enabled by default, and will work with any supported model. You are guaranteed a validly-parsable function call - not a 
+high-quality one. 
+
+To use a named function, you need to define the functions in the `tools` parameter of the chat completion request, and 
+specify the `name` of one of the tools in the `tool_choice` parameter of the chat completion request. 
+
+### Config file
+
+The `serve` module can also accept arguments from a config file in
+`yaml` format. The arguments in the yaml must be specified using the 
+long form of the argument outlined [here](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#command-line-arguments-for-the-server): 
+
+For example:
+
+```yaml
+# config.yaml
+
+host: "127.0.0.1"
+port: 6379
+uvicorn-log-level: "info"
+```
+
+```bash
+$ vllm serve SOME_MODEL --config config.yaml
+```
+---
+**NOTE**  
+In case an argument is supplied simultaneously using command line and the config file, the value from the commandline will take precedence.
+The order of priorities is `command line > config file values > defaults`.
+
+---
 
 ## Tool calling in the chat completion API
 vLLM supports only named function calling in the chat completion API. The `tool_choice` options `auto` and `required` are **not yet supported** but on the roadmap.
 
-To use a named function you need to define the function in the `tools` parameter and call it in the `tool_choice` parameter. 
-
-It is the callers responsibility to prompt the model with the tool information, vLLM will not automatically manipulate the prompt. **This may change in the future.**
+It is the callers responsibility to prompt the model with the tool information, vLLM will not automatically manipulate the prompt.
 
 vLLM will use guided decoding to ensure the response matches the tool parameter object defined by the JSON schema in the `tools` parameter.
 
-Please refer to the OpenAI API reference documentation for more information.
+
+### Automatic Function Calling
+To enable this feature, you should set the following flags:
+* `--enable-auto-tool-choice` -- **mandatory** Auto tool choice. tells vLLM that you want to enable the model to generate its own tool calls when it 
+deems appropriate.
+* `--tool-call-parser` -- select the tool parser to use - currently either `hermes` or `mistral` or `llama3_json` or `internlm`. Additional tool parsers 
+will continue to be added in the future, and also can register your own tool parsers in the `--tool-parser-plugin`.
+* `--tool-parser-plugin` -- **optional** tool parser plugin used to register user defined tool parsers into vllm, the registered tool parser name can be specified in `--tool-call-parser`.
+* `--chat-template` -- **optional** for auto tool choice. the path to the chat template which handles `tool`-role messages and `assistant`-role messages 
+that contain previously generated tool calls. Hermes, Mistral and Llama models have tool-compatible chat templates in their 
+`tokenizer_config.json` files, but you can specify a custom template. This argument can be set to `tool_use` if your model has a tool use-specific chat 
+template configured in the `tokenizer_config.json`. In this case, it will be used per the `transformers` specification. More on this [here](https://huggingface.co/docs/transformers/en/chat_templating#why-do-some-models-have-multiple-templates)
+from HuggingFace; and you can find an example of this in a `tokenizer_config.json` [here](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B/blob/main/tokenizer_config.json)
+
+If your favorite tool-calling model is not supported, please feel free to contribute a parser & tool use chat template! 
+
+#### Hermes Models
+All Nous Research Hermes-series models newer than Hermes 2 Pro should be supported.
+* `NousResearch/Hermes-2-Pro-*`
+* `NousResearch/Hermes-2-Theta-*`
+* `NousResearch/Hermes-3-*`
+
+
+_Note that the Hermes 2 **Theta** models are known to have degraded tool call quality & capabilities due to the merge 
+step in their creation_. 
+
+Flags: `--tool-call-parser hermes`
+
+#### Mistral Models
+Supported models:
+* `mistralai/Mistral-7B-Instruct-v0.3` (confirmed)
+* Additional mistral function-calling models are compatible as well.
+
+Known issues:
+1. Mistral 7B struggles to generate parallel tool calls correctly. 
+2. Mistral's `tokenizer_config.json` chat template requires tool call IDs that are exactly 9 digits, which is 
+much shorter than what vLLM generates. Since an exception is thrown when this condition 
+is not met, the following additional chat templates are provided:
+
+* `examples/tool_chat_template_mistral.jinja` - this is the "official" Mistral chat template, but tweaked so that
+it works with vLLM's tool call IDs (provided `tool_call_id` fields are truncated to the last 9 digits)
+* `examples/tool_chat_template_mistral_parallel.jinja` - this is a "better" version that adds a tool-use system prompt
+when tools are provided, that results in much better reliability when working with parallel tool calling.
+
+
+Recommended flags: `--tool-call-parser mistral --chat-template examples/tool_chat_template_mistral_parallel.jinja`
+
+#### Llama Models
+Supported models:
+* `meta-llama/Meta-Llama-3.1-8B-Instruct`
+* `meta-llama/Meta-Llama-3.1-70B-Instruct`
+* `meta-llama/Meta-Llama-3.1-405B-Instruct`
+* `meta-llama/Meta-Llama-3.1-405B-Instruct-FP8`
+
+The tool calling that is supported is the [JSON based tool calling](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/#json-based-tool-calling).
+Other tool calling formats like the built in python tool calling or custom tool calling are not supported.
+
+Known issues:
+1. Parallel tool calls are not supported. 
+2. The model can generate parameters with a wrong format, such as generating
+   an array serialized as string instead of an array.
+
+The `tool_chat_template_llama3_json.jinja` file contains the "official" Llama chat template, but tweaked so that
+it works better with vLLM.
+
+Recommended flags: `--tool-call-parser llama3_json --chat-template examples/tool_chat_template_llama3_json.jinja`
+
+#### Internlm Models
+Supported models:
+* `internlm/internlm2_5-7b-chat` (confirmed)
+* Additional internlm2.5 function-calling models are compatible as well
+
+Known issues:
+* Although this implementation also supports Internlm2, the tool call results are not stable when testing with the `internlm/internlm2-chat-7b` model.
+
+Recommended flags: `--tool-call-parser internlm --chat-template examples/tool_chat_template_internlm2_tool.jinja`
+
+
+### How to write a tool parser plugin
+
+A tool parser plugin is a Python file containing one or more ToolParser implementations. You can write a ToolParser similar to the `Hermes2ProToolParser` in vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py.
+
+Here is a summary of a plugin file:
+
+```python
+
+# import the required packages
+
+# define a tool parser and register it to vllm
+# the name list in register_module can be used
+# in --tool-call-parser. you can define as many
+# tool parsers as you want here.
+@ToolParserManager.register_module(["example"])
+class ExampleToolParser(ToolParser):
+    def __init__(self, tokenizer: AnyTokenizer):
+        super().__init__(tokenizer)
+
+    # adjust request. e.g.: set skip special tokens
+    # to False for tool call output.
+    def adjust_request(
+            self, request: ChatCompletionRequest) -> ChatCompletionRequest:
+        return request
+
+    # implement the tool call parse for stream call
+    def extract_tool_calls_streaming(
+        self,
+        previous_text: str,
+        current_text: str,
+        delta_text: str,
+        previous_token_ids: Sequence[int],
+        current_token_ids: Sequence[int],
+        delta_token_ids: Sequence[int],
+        request: ChatCompletionRequest,
+    ) -> Union[DeltaMessage, None]:
+        return delta
+
+    # implement the tool parse for non-stream call
+    def extract_tool_calls(
+        self,
+        model_output: str,
+        request: ChatCompletionRequest,
+    ) -> ExtractedToolCallInformation:
+        return ExtractedToolCallInformation(tools_called=False,
+                                            tool_calls=[],
+                                            content=text)
+
+
+```
+
+Then you can use this plugin in the command line like this.
+```
+    --enable-auto-tool-choice \
+    --tool-parser-plugin <absolute path of the plugin file>
+    --tool-call-parser example \
+    --chat-template <your chat template> \
+``` 
+

docs/source/serving/serving_with_llamaindex.rst

+.. _run_on_llamaindex:
+
+Serving with llama_index
+============================
+
+vLLM is also available via `llama_index <https://github.com/run-llama/llama_index>`_ .
+
+To install llamaindex, run
+
+.. code-block:: console
+
+    $ pip install llama-index-llms-vllm -q
+
+To run inference on a single or multiple GPUs, use ``Vllm`` class from ``llamaindex``.
+
+.. code-block:: python
+
+    from llama_index.llms.vllm import Vllm
+
+    llm = Vllm(
+        model="microsoft/Orca-2-7b",
+        tensor_parallel_size=4,
+        max_new_tokens=100,
+        vllm_kwargs={"swap_space": 1, "gpu_memory_utilization": 0.5},
+    )
+
+Please refer to this `Tutorial <https://docs.llamaindex.ai/en/latest/examples/llm/vllm/>`_ for more details.

examples/fp8/README.md

@@ -62,7 +62,7 @@ This script evaluates the inference throughput of language models using various
 
 python3 benchmarks/benchmark_throughput.py --help 
 usage: benchmark_throughput.py [-h] [--backend {vllm,hf,mii}] [--dataset DATASET] [--input-len INPUT_LEN] [--output-len OUTPUT_LEN] [--model MODEL]
-                               [--tokenizer TOKENIZER] [--quantization {awq,gptq,squeezellm,None}] [--tensor-parallel-size TENSOR_PARALLEL_SIZE] [--n N]
+                               [--tokenizer TOKENIZER] [--quantization {awq,gptq,None}] [--tensor-parallel-size TENSOR_PARALLEL_SIZE] [--n N]
                                [--use-beam-search] [--num-prompts NUM_PROMPTS] [--seed SEED] [--hf-max-batch-size HF_MAX_BATCH_SIZE] [--trust-remote-code]
                                [--max-model-len MAX_MODEL_LEN] [--dtype {auto,half,float16,bfloat16,float,float32}] [--enforce-eager] [--kv-cache-dtype {auto,fp8}]
                                [--quantization-param-path KV_CACHE_quantization_param_path]
@@ -76,7 +76,7 @@ optional arguments:
   --output-len OUTPUT_LEN  Output length for each request. Overrides the output length from the dataset.
   --model MODEL
   --tokenizer TOKENIZER
-  --quantization {awq,gptq,squeezellm,None}, -q {awq,gptq,squeezellm,None}
+  --quantization {awq,gptq,None}, -q {awq,gptq,None}
   --tensor-parallel-size TENSOR_PARALLEL_SIZE, -tp TENSOR_PARALLEL_SIZE
   --n N  Number of generated sequences per prompt.
   --use-beam-search

examples/fp8/quantizer/README.md

 ### Quantizer Utilities
-`quantize.py`: NVIDIA Quantization utilities using AMMO, ported from TensorRT-LLM:
-`https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/quantization/quantize.py`
+`quantize.py`: NVIDIA Quantization utilities using TensorRT-Model-Optimizer, ported
+from TensorRT-LLM: [`examples/quantization/quantize.py`](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/quantization/quantize.py)
 
 ### Prerequisite
 

examples/gguf_inference.py

+from huggingface_hub import hf_hub_download
+
+from vllm import LLM, SamplingParams
+
+
+def run_gguf_inference(model_path):
+    PROMPT_TEMPLATE = "<|system|>\n{system_message}</s>\n<|user|>\n{prompt}</s>\n<|assistant|>\n"  # noqa: E501
+    system_message = "You are a friendly chatbot who always responds in the style of a pirate."  # noqa: E501
+    # Sample prompts.
+    prompts = [
+        "How many helicopters can a human eat in one sitting?",
+        "What's the future of AI?",
+    ]
+    prompts = [
+        PROMPT_TEMPLATE.format(system_message=system_message, prompt=prompt)
+        for prompt in prompts
+    ]
+    # Create a sampling params object.
+    sampling_params = SamplingParams(temperature=0, max_tokens=128)
+
+    # Create an LLM.
+    llm = LLM(model=model_path,
+              tokenizer="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+              gpu_memory_utilization=0.95)
+
+    outputs = llm.generate(prompts, sampling_params)
+    # Print the outputs.
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+
+if __name__ == "__main__":
+    repo_id = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
+    filename = "tinyllama-1.1b-chat-v1.0.Q4_0.gguf"
+    model = hf_hub_download(repo_id, filename=filename)
+    run_gguf_inference(model)

examples/llm_engine_example.py

@@ -18,9 +18,6 @@ def create_test_prompts() -> List[Tuple[str, SamplingParams]]:
                         temperature=0.8,
                         top_p=0.95,
                         frequency_penalty=0.1)),
-        ("It is only with the heart that one can see rightly",
-         SamplingParams(n=3, best_of=3, use_beam_search=True,
-                        temperature=0.0)),
     ]
 
 

examples/lora_with_quantization_inference.py

@@ -79,23 +79,17 @@ def initialize_engine(model: str, quantization: str,
         # It quantizes the model when loading, with some config info from the
         # LoRA adapter repo. So need to set the parameter of load_format and
         # qlora_adapter_name_or_path as below.
-        engine_args = EngineArgs(
-            model=model,
-            quantization=quantization,
-            qlora_adapter_name_or_path=lora_repo,
-            load_format="bitsandbytes",
-            enable_lora=True,
-            max_lora_rank=64,
-            # set it only in GPUs of limited memory
-            enforce_eager=True)
+        engine_args = EngineArgs(model=model,
+                                 quantization=quantization,
+                                 qlora_adapter_name_or_path=lora_repo,
+                                 load_format="bitsandbytes",
+                                 enable_lora=True,
+                                 max_lora_rank=64)
     else:
-        engine_args = EngineArgs(
-            model=model,
-            quantization=quantization,
-            enable_lora=True,
-            max_loras=4,
-            # set it only in GPUs of limited memory
-            enforce_eager=True)
+        engine_args = EngineArgs(model=model,
+                                 quantization=quantization,
+                                 enable_lora=True,
+                                 max_loras=4)
     return LLMEngine.from_engine_args(engine_args)
 
 

examples/multilora_inference.py

@@ -43,15 +43,6 @@ def create_test_prompts(
                            max_tokens=128,
                            stop_token_ids=[32003]),
             LoRARequest("sql-lora", 1, lora_path)),
-        (
-            "[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]",  # noqa: E501
-            SamplingParams(n=3,
-                           best_of=3,
-                           use_beam_search=True,
-                           temperature=0,
-                           max_tokens=128,
-                           stop_token_ids=[32003]),
-            LoRARequest("sql-lora", 1, lora_path)),
         (
             "[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\n question: Name the ICAO for lilongwe international airport [/user] [assistant]",  # noqa: E501
             SamplingParams(temperature=0.0,
@@ -60,15 +51,6 @@ def create_test_prompts(
                            max_tokens=128,
                            stop_token_ids=[32003]),
             LoRARequest("sql-lora2", 2, lora_path)),
-        (
-            "[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]",  # noqa: E501
-            SamplingParams(n=3,
-                           best_of=3,
-                           use_beam_search=True,
-                           temperature=0,
-                           max_tokens=128,
-                           stop_token_ids=[32003]),
-            LoRARequest("sql-lora", 1, lora_path)),
     ]
 
 

examples/offline_chat_with_tools.py

+# ruff: noqa
+import json
+import random
+import string
+
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
+
+# This script is an offline demo for function calling
+#
+# If you want to run a server/client setup, please follow this code:
+#
+# - Server:
+#
+# ```bash
+# vllm serve mistralai/Mistral-7B-Instruct-v0.3 --tokenizer-mode mistral --load-format mistral --config-format mistral
+# ```
+#
+# - Client:
+#
+# ```bash
+# curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
+# --header 'Content-Type: application/json' \
+# --header 'Authorization: Bearer token' \
+# --data '{
+#     "model": "mistralai/Mistral-7B-Instruct-v0.3"
+#     "messages": [
+#       {
+#         "role": "user",
+#         "content": [
+#             {"type" : "text", "text": "Describe this image in detail please."},
+#             {"type": "image_url", "image_url": {"url": "https://s3.amazonaws.com/cms.ipressroom.com/338/files/201808/5b894ee1a138352221103195_A680%7Ejogging-edit/A680%7Ejogging-edit_hero.jpg"}},
+#             {"type" : "text", "text": "and this one as well. Answer in French."},
+#             {"type": "image_url", "image_url": {"url": "https://www.wolframcloud.com/obj/resourcesystem/images/a0e/a0ee3983-46c6-4c92-b85d-059044639928/6af8cfb971db031b.png"}}
+#         ]
+#       }
+#     ]
+#   }'
+# ```
+#
+# Usage:
+#     python demo.py simple
+#     python demo.py advanced
+
+model_name = "mistralai/Mistral-7B-Instruct-v0.3"
+# or switch to "mistralai/Mistral-Nemo-Instruct-2407"
+# or "mistralai/Mistral-Large-Instruct-2407"
+# or any other mistral model with function calling ability
+
+sampling_params = SamplingParams(max_tokens=8192, temperature=0.0)
+llm = LLM(model=model_name,
+          tokenizer_mode="mistral",
+          config_format="mistral",
+          load_format="mistral")
+
+
+def generate_random_id(length=9):
+    characters = string.ascii_letters + string.digits
+    random_id = ''.join(random.choice(characters) for _ in range(length))
+    return random_id
+
+
+# simulate an API that can be called
+def get_current_weather(city: str, state: str, unit: 'str'):
+    return (f"The weather in {city}, {state} is 85 degrees {unit}. It is "
+            "partly cloudly, with highs in the 90's.")
+
+
+tool_funtions = {"get_current_weather": get_current_weather}
+
+tools = [{
+    "type": "function",
+    "function": {
+        "name": "get_current_weather",
+        "description": "Get the current weather in a given location",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "city": {
+                    "type":
+                    "string",
+                    "description":
+                    "The city to find the weather for, e.g. 'San Francisco'"
+                },
+                "state": {
+                    "type":
+                    "string",
+                    "description":
+                    "the two-letter abbreviation for the state that the city is"
+                    " in, e.g. 'CA' which would mean 'California'"
+                },
+                "unit": {
+                    "type": "string",
+                    "description": "The unit to fetch the temperature in",
+                    "enum": ["celsius", "fahrenheit"]
+                }
+            },
+            "required": ["city", "state", "unit"]
+        }
+    }
+}]
+
+messages = [{
+    "role":
+    "user",
+    "content":
+    "Can you tell me what the temperate will be in Dallas, in fahrenheit?"
+}]
+
+outputs = llm.chat(messages, sampling_params=sampling_params, tools=tools)
+output = outputs[0].outputs[0].text.strip()
+
+# append the assistant message
+messages.append({
+    "role": "assistant",
+    "content": output,
+})
+
+# let's now actually parse and execute the model's output simulating an API call by using the
+# above defined function
+tool_calls = json.loads(output)
+tool_answers = [
+    tool_funtions[call['name']](**call['arguments']) for call in tool_calls
+]
+
+# append the answer as a tool message and let the LLM give you an answer
+messages.append({
+    "role": "tool",
+    "content": "\n\n".join(tool_answers),
+    "tool_call_id": generate_random_id(),
+})
+
+outputs = llm.chat(messages, sampling_params, tools=tools)
+
+print(outputs[0].outputs[0].text.strip())
+# yields
+#   'The weather in Dallas, TX is 85 degrees fahrenheit. '
+#   'It is partly cloudly, with highs in the 90's.'

examples/offline_inference.py

 from vllm import LLM, SamplingParams
 
-if __name__ == '__main__':
-    # Sample prompts.
-    prompts = [
-        "Hello, my name is",
-        "The president of the United States is",
-        "The capital of France is",
-        "The future of AI is",
-    ]
-    # Create a sampling params object.
-    sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
 
-    # Create an LLM.
-    llm = LLM(model="facebook/opt-125m",tensor_parallel_size=1, distributed_executor_backend="ray", dtype="float16",trust_remote_code=True, enforce_eager=True)
-    # Generate texts from the prompts. The output is a list of RequestOutput objects
-    # that contain the prompt, generated text, and other information.
-    outputs = llm.generate(prompts, sampling_params)
-    # Print the outputs.
-    for output in outputs:
-        prompt = output.prompt
-        generated_text = output.outputs[0].text
-        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+# Create an LLM.
+llm = LLM(model="facebook/opt-125m",tensor_parallel_size=1, distributed_executor_backend="ray", dtype="float16",trust_remote_code=True, enforce_eager=True)
+# Generate texts from the prompts. The output is a list of RequestOutput objects
+# that contain the prompt, generated text, and other information.
+outputs = llm.generate(prompts, sampling_params)
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

examples/offline_inference_audio_language.py

+"""
+This example shows how to use vLLM for running offline inference 
+with the correct prompt format on audio language models.
+
+For most models, the prompt format should follow corresponding examples
+on HuggingFace model repository.
+"""
+from transformers import AutoTokenizer
+
+from vllm import LLM, SamplingParams
+from vllm.assets.audio import AudioAsset
+from vllm.utils import FlexibleArgumentParser
+
+audio_assets = [AudioAsset("mary_had_lamb"), AudioAsset("winning_call")]
+question_per_audio_count = [
+    "What is recited in the audio?",
+    "What sport and what nursery rhyme are referenced?"
+]
+
+
+# Ultravox 0.3
+def run_ultravox(question, audio_count):
+    model_name = "fixie-ai/ultravox-v0_3"
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    messages = [{
+        'role':
+        'user',
+        'content':
+        "<|reserved_special_token_0|>\n" * audio_count + question
+    }]
+    prompt = tokenizer.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True)
+
+    llm = LLM(model=model_name,
+              enforce_eager=True,
+              enable_chunked_prefill=False,
+              max_model_len=8192,
+              limit_mm_per_prompt={"audio": audio_count})
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+model_example_map = {
+    "ultravox": run_ultravox,
+}
+
+
+def main(args):
+    model = args.model_type
+    if model not in model_example_map:
+        raise ValueError(f"Model type {model} is not supported.")
+
+    audio_count = args.num_audios
+    llm, prompt, stop_token_ids = model_example_map[model](
+        question_per_audio_count[audio_count - 1], audio_count)
+
+    # We set temperature to 0.2 so that outputs can be different
+    # even when all prompts are identical when running batch inference.
+    sampling_params = SamplingParams(temperature=0.2,
+                                     max_tokens=64,
+                                     stop_token_ids=stop_token_ids)
+
+    assert args.num_prompts > 0
+    inputs = {
+        "prompt": prompt,
+        "multi_modal_data": {
+            "audio": [
+                asset.audio_and_sample_rate
+                for asset in audio_assets[:audio_count]
+            ]
+        },
+    }
+    if args.num_prompts > 1:
+        # Batch inference
+        inputs = [inputs] * args.num_prompts
+
+    outputs = llm.generate(inputs, sampling_params=sampling_params)
+
+    for o in outputs:
+        generated_text = o.outputs[0].text
+        print(generated_text)
+
+
+if __name__ == "__main__":
+    parser = FlexibleArgumentParser(
+        description='Demo on using vLLM for offline inference with '
+        'audio language models')
+    parser.add_argument('--model-type',
+                        '-m',
+                        type=str,
+                        default="ultravox",
+                        choices=model_example_map.keys(),
+                        help='Huggingface "model_type".')
+    parser.add_argument('--num-prompts',
+                        type=int,
+                        default=1,
+                        help='Number of prompts to run.')
+    parser.add_argument("--num-audios",
+                        type=int,
+                        default=1,
+                        choices=[1, 2],
+                        help="Number of audio items per prompt.")
+
+    args = parser.parse_args()
+    main(args)

examples/offline_inference_chat.py

+from vllm import LLM, SamplingParams
+
+llm = LLM(model="meta-llama/Meta-Llama-3-8B-Instruct")
+sampling_params = SamplingParams(temperature=0.5)
+
+
+def print_outputs(outputs):
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+    print("-" * 80)
+
+
+print("=" * 80)
+
+# In this script, we demonstrate how to pass input to the chat method:
+
+conversation = [
+    {
+        "role": "system",
+        "content": "You are a helpful assistant"
+    },
+    {
+        "role": "user",
+        "content": "Hello"
+    },
+    {
+        "role": "assistant",
+        "content": "Hello! How can I assist you today?"
+    },
+    {
+        "role": "user",
+        "content": "Write an essay about the importance of higher education.",
+    },
+]
+outputs = llm.chat(conversation,
+                   sampling_params=sampling_params,
+                   use_tqdm=False)
+print_outputs(outputs)
+
+# You can run batch inference with llm.chat API
+conversation = [
+    {
+        "role": "system",
+        "content": "You are a helpful assistant"
+    },
+    {
+        "role": "user",
+        "content": "Hello"
+    },
+    {
+        "role": "assistant",
+        "content": "Hello! How can I assist you today?"
+    },
+    {
+        "role": "user",
+        "content": "Write an essay about the importance of higher education.",
+    },
+]
+conversations = [conversation for _ in range(10)]
+
+# We turn on tqdm progress bar to verify it's indeed running batch inference
+outputs = llm.chat(messages=conversations,
+                   sampling_params=sampling_params,
+                   use_tqdm=True)
+print_outputs(outputs)
+
+# A chat template can be optionally supplied.
+# If not, the model will use its default chat template.
+
+# with open('template_falcon_180b.jinja', "r") as f:
+#     chat_template = f.read()
+
+# outputs = llm.chat(
+#     conversations,
+#     sampling_params=sampling_params,
+#     use_tqdm=False,
+#     chat_template=chat_template,
+# )

examples/offline_inference_encoder_decoder.py

+'''
+Demonstrate prompting of text-to-text
+encoder/decoder models, specifically BART
+'''
+
+from vllm import LLM, SamplingParams
+from vllm.inputs import (ExplicitEncoderDecoderPrompt, TextPrompt,
+                         TokensPrompt, zip_enc_dec_prompts)
+
+dtype = "float"
+
+# Create a BART encoder/decoder model instance
+llm = LLM(
+    model="facebook/bart-large-cnn",
+    dtype=dtype,
+)
+
+# Get BART tokenizer
+tokenizer = llm.llm_engine.get_tokenizer_group()
+
+# Test prompts
+#
+# This section shows all of the valid ways to prompt an
+# encoder/decoder model.
+#
+# - Helpers for building prompts
+text_prompt_raw = "Hello, my name is"
+text_prompt = TextPrompt(prompt="The president of the United States is")
+tokens_prompt = TokensPrompt(prompt_token_ids=tokenizer.encode(
+    prompt="The capital of France is"))
+# - Pass a single prompt to encoder/decoder model
+#   (implicitly encoder input prompt);
+#   decoder input prompt is assumed to be None
+
+single_text_prompt_raw = text_prompt_raw  # Pass a string directly
+single_text_prompt = text_prompt  # Pass a TextPrompt
+single_tokens_prompt = tokens_prompt  # Pass a TokensPrompt
+
+# - Pass explicit encoder and decoder input prompts within one data structure.
+#   Encoder and decoder prompts can both independently be text or tokens, with
+#   no requirement that they be the same prompt type. Some example prompt-type
+#   combinations are shown below, note that these are not exhaustive.
+
+enc_dec_prompt1 = ExplicitEncoderDecoderPrompt(
+    # Pass encoder prompt string directly, &
+    # pass decoder prompt tokens
+    encoder_prompt=single_text_prompt_raw,
+    decoder_prompt=single_tokens_prompt,
+)
+enc_dec_prompt2 = ExplicitEncoderDecoderPrompt(
+    # Pass TextPrompt to encoder, and
+    # pass decoder prompt string directly
+    encoder_prompt=single_text_prompt,
+    decoder_prompt=single_text_prompt_raw,
+)
+enc_dec_prompt3 = ExplicitEncoderDecoderPrompt(
+    # Pass encoder prompt tokens directly, and
+    # pass TextPrompt to decoder
+    encoder_prompt=single_tokens_prompt,
+    decoder_prompt=single_text_prompt,
+)
+
+# - Finally, here's a useful helper function for zipping encoder and
+#   decoder prompts together into a list of ExplicitEncoderDecoderPrompt
+#   instances
+zipped_prompt_list = zip_enc_dec_prompts(
+    ['An encoder prompt', 'Another encoder prompt'],
+    ['A decoder prompt', 'Another decoder prompt'])
+
+# - Let's put all of the above example prompts together into one list
+#   which we will pass to the encoder/decoder LLM.
+prompts = [
+    single_text_prompt_raw, single_text_prompt, single_tokens_prompt,
+    enc_dec_prompt1, enc_dec_prompt2, enc_dec_prompt3
+] + zipped_prompt_list
+
+print(prompts)
+
+# Create a sampling params object.
+sampling_params = SamplingParams(
+    temperature=0,
+    top_p=1.0,
+    min_tokens=0,
+    max_tokens=20,
+)
+
+# Generate output tokens from the prompts. The output is a list of
+# RequestOutput objects that contain the prompt, generated
+# text, and other information.
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    encoder_prompt = output.encoder_prompt
+    generated_text = output.outputs[0].text
+    print(f"Encoder prompt: {encoder_prompt!r}, "
+          f"Decoder prompt: {prompt!r}, "
+          f"Generated text: {generated_text!r}")

examples/offline_inference_mlpspeculator.py

@@ -50,8 +50,6 @@ if __name__ == "__main__":
     llm = LLM(
         model="meta-llama/Llama-2-13b-chat-hf",
         speculative_model="ibm-fms/llama-13b-accelerator",
-        # These are currently required for MLPSpeculator decoding
-        use_v2_block_manager=True,
     )
 
     print("With speculation")

examples/offline_inference_neuron.py

+import os
+
 from vllm import LLM, SamplingParams
 
+# creates XLA hlo graphs for all the context length buckets.
+os.environ['NEURON_CONTEXT_LENGTH_BUCKETS'] = "128,512,1024,2048"
+# creates XLA hlo graphs for all the token gen buckets.
+os.environ['NEURON_TOKEN_GEN_BUCKETS'] = "128,512,1024,2048"
+
 # Sample prompts.
 prompts = [
     "Hello, my name is",
@@ -19,8 +26,8 @@ llm = LLM(
     # Currently, this is a known limitation in continuous batching support
     # in transformers-neuronx.
     # TODO(liangfu): Support paged-attention in transformers-neuronx.
-    max_model_len=128,
-    block_size=128,
+    max_model_len=2048,
+    block_size=2048,
     # The device can be automatically detected when AWS Neuron SDK is installed.
     # The device argument can be either unspecified for automated detection,
     # or explicitly assigned.

examples/offline_inference_neuron_int8_quantization.py

+import os
+
+from vllm import LLM, SamplingParams
+
+# creates XLA hlo graphs for all the context length buckets.
+os.environ['NEURON_CONTEXT_LENGTH_BUCKETS'] = "128,512,1024,2048"
+# creates XLA hlo graphs for all the token gen buckets.
+os.environ['NEURON_TOKEN_GEN_BUCKETS'] = "128,512,1024,2048"
+# Quantizes neuron model weight to int8 ,
+# The default config for quantization is int8 dtype.
+os.environ['NEURON_QUANT_DTYPE'] = "s8"
+
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+# Create an LLM.
+llm = LLM(
+    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+    max_num_seqs=8,
+    # The max_model_len and block_size arguments are required to be same as
+    # max sequence length when targeting neuron device.
+    # Currently, this is a known limitation in continuous batching support
+    # in transformers-neuronx.
+    # TODO(liangfu): Support paged-attention in transformers-neuronx.
+    max_model_len=2048,
+    block_size=2048,
+    # The device can be automatically detected when AWS Neuron SDK is installed.
+    # The device argument can be either unspecified for automated detection,
+    # or explicitly assigned.
+    device="neuron",
+    quantization="neuron_quant",
+    override_neuron_config={
+        "cast_logits_dtype": "bfloat16",
+    },
+    tensor_parallel_size=2)
+# Generate texts from the prompts. The output is a list of RequestOutput objects
+# that contain the prompt, generated text, and other information.
+outputs = llm.generate(prompts, sampling_params)
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

examples/offline_inference_openai.md

@@ -10,7 +10,7 @@
  
  Each line represents a separate request. See the [OpenAI package reference](https://platform.openai.com/docs/api-reference/batch/requestInput) for more details.
  
- **NOTE:** We currently only support to `/v1/chat/completions` endpoint (embeddings and completions coming soon).
+ **NOTE:** We currently only support `/v1/chat/completions` and `/v1/embeddings` endpoints (completions coming soon).
  
  ## Pre-requisites
  
@@ -21,7 +21,7 @@
   - Get access to the gated model by [visiting the model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) and agreeing to the terms and conditions.
  
  
- ## Example: Running with a local file
+ ## Example 1: Running with a local file
  
  ### Step 1: Create your batch file
  
@@ -54,7 +54,7 @@ python -m vllm.entrypoints.openai.run_batch -i openai_example_batch.jsonl -o res
 You should now have your results at `results.jsonl`. You can check your results by running `cat results.jsonl`
 
 ```
-$ cat ../results.jsonl
+$ 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}
 ```
@@ -107,7 +107,7 @@ aws s3 cp openai_example_batch.jsonl s3://MY_BUCKET/MY_INPUT_FILE.jsonl
   
 ### Step 2: Generate your presigned urls
 
-Presigned put urls can only be generated via the SDK. You can run the following python script to generate your presigned urls. Be sure to replace the `MY_BUCKET`, `MY_INPUT_FILE.jsonl`, and `MY_OUTPUT_FILE.jsonl` placeholders with your bucket and file names.
+Presigned urls can only be generated via the SDK. You can run the following python script to generate your presigned urls. Be sure to replace the `MY_BUCKET`, `MY_INPUT_FILE.jsonl`, and `MY_OUTPUT_FILE.jsonl` placeholders with your bucket and file names.
 
 (The script is adapted from https://github.com/awsdocs/aws-doc-sdk-examples/blob/main/python/example_code/s3/s3_basics/presigned_url.py)
 
@@ -170,3 +170,36 @@ Your results are now on S3. You can view them in your terminal by running
 ```
 aws s3 cp s3://MY_BUCKET/MY_OUTPUT_FILE.jsonl -
 ```
+
+## Example 4: Using embeddings endpoint
+
+### Additional prerequisites
+
+* Ensure you are using `vllm >= 0.5.5`.
+
+### Step 1: Create your batch file
+ 
+ Add embedding requests to your batch file. The following is an example:
+ 
+ ```
+ {"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are a helpful assistant."}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are an unhelpful assistant."}}
+```
+ 
+ You can even mix chat completion and embedding requests in the batch file, as long as the model you are using supports both chat completion and embeddings (note that all requests must use the same model).
+
+
+ ### Step 2: Run the batch
+
+You can run the batch using the same command as in earlier examples.
+
+
+### Step 3: Check your results
+
+You can check your results by running `cat results.jsonl`
+
+```
+$ 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}
+...```
+```