init qwen3

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

+import gc
+import time
+from typing import List
+
+from vllm import LLM, SamplingParams
+
+
+def time_generation(llm: LLM, prompts: List[str],
+                    sampling_params: SamplingParams):
+    # Generate texts from the prompts. The output is a list of RequestOutput
+    # objects that contain the prompt, generated text, and other information.
+    # Warmup first
+    llm.generate(prompts, sampling_params)
+    llm.generate(prompts, sampling_params)
+    start = time.time()
+    outputs = llm.generate(prompts, sampling_params)
+    end = time.time()
+    print((end - start) / sum([len(o.outputs[0].token_ids) for o in outputs]))
+    # Print the outputs.
+    for output in outputs:
+        generated_text = output.outputs[0].text
+        print(f"text: {generated_text!r}")
+
+
+if __name__ == "__main__":
+
+    template = (
+        "Below is an instruction that describes a task. Write a response "
+        "that appropriately completes the request.\n\n### Instruction:\n{}"
+        "\n\n### Response:\n")
+
+    # Sample prompts.
+    prompts = [
+        "Write about the president of the United States.",
+    ]
+    prompts = [template.format(prompt) for prompt in prompts]
+    # Create a sampling params object.
+    sampling_params = SamplingParams(temperature=0.0, max_tokens=200)
+
+    # Create an LLM without spec decoding
+    llm = LLM(model="meta-llama/Llama-2-13b-chat-hf")
+
+    print("Without speculation")
+    time_generation(llm, prompts, sampling_params)
+
+    del llm
+    gc.collect()
+
+    # Create an LLM with spec decoding
+    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")
+    time_generation(llm, prompts, sampling_params)

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_pixtral.py

+# ruff: noqa
+import argparse
+
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
+
+# This script is an offline demo for running Pixtral.
+#
+# If you want to run a server/client setup, please follow this code:
+#
+# - Server:
+#
+# ```bash
+# vllm serve mistralai/Pixtral-12B-2409 --tokenizer-mode mistral --limit-mm-per-prompt 'image=4' --max-model-len 16384
+# ```
+#
+# - Client:
+#
+# ```bash
+# curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
+# --header 'Content-Type: application/json' \
+# --header 'Authorization: Bearer token' \
+# --data '{
+#     "model": "mistralai/Pixtral-12B-2409",
+#     "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
+
+
+def run_simple_demo():
+    model_name = "mistralai/Pixtral-12B-2409"
+    sampling_params = SamplingParams(max_tokens=8192)
+
+    # Lower max_num_seqs or max_model_len on low-VRAM GPUs.
+    llm = LLM(model=model_name, tokenizer_mode="mistral")
+
+    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
+                    }
+                },
+            ],
+        },
+    ]
+    outputs = llm.chat(messages, sampling_params=sampling_params)
+
+    print(outputs[0].outputs[0].text)
+
+
+def run_advanced_demo():
+    model_name = "mistralai/Pixtral-12B-2409"
+    max_img_per_msg = 5
+    max_tokens_per_img = 4096
+
+    sampling_params = SamplingParams(max_tokens=8192, temperature=0.7)
+    llm = LLM(
+        model=model_name,
+        tokenizer_mode="mistral",
+        limit_mm_per_prompt={"image": max_img_per_msg},
+        max_model_len=max_img_per_msg * max_tokens_per_img,
+    )
+
+    prompt = "Describe the following image."
+
+    url_1 = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
+    url_2 = "https://picsum.photos/seed/picsum/200/300"
+    url_3 = "https://picsum.photos/id/32/512/512"
+
+    messages = [
+        {
+            "role":
+            "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": prompt
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": url_1
+                    }
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": url_2
+                    }
+                },
+            ],
+        },
+        {
+            "role": "assistant",
+            "content": "The images show nature.",
+        },
+        {
+            "role": "user",
+            "content": "More details please and answer only in French!.",
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": url_3
+                    }
+                },
+            ],
+        },
+    ]
+
+    outputs = llm.chat(messages=messages, sampling_params=sampling_params)
+    print(outputs[0].outputs[0].text)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Run a demo in simple or advanced mode.")
+
+    parser.add_argument(
+        "mode",
+        choices=["simple", "advanced"],
+        help="Specify the demo mode: 'simple' or 'advanced'",
+    )
+
+    args = parser.parse_args()
+
+    if args.mode == "simple":
+        print("Running simple demo...")
+        run_simple_demo()
+    elif args.mode == "advanced":
+        print("Running advanced demo...")
+        run_advanced_demo()
+
+
+if __name__ == "__main__":
+    main()

examples/offline_inference_tpu.py

+from vllm import LLM, SamplingParams
+
+prompts = [
+    "A robot may not injure a human being",
+    "It is only with the heart that one can see rightly;",
+    "The greatest glory in living lies not in never falling,",
+]
+answers = [
+    " or, through inaction, allow a human being to come to harm.",
+    " what is essential is invisible to the eye.",
+    " but in rising every time we fall.",
+]
+N = 1
+# Currently, top-p sampling is disabled. `top_p` should be 1.0.
+sampling_params = SamplingParams(temperature=0.7,
+                                 top_p=1.0,
+                                 n=N,
+                                 max_tokens=16)
+
+# Set `enforce_eager=True` to avoid ahead-of-time compilation.
+# In real workloads, `enforace_eager` should be `False`.
+llm = LLM(model="google/gemma-2b", enforce_eager=True)
+outputs = llm.generate(prompts, sampling_params)
+for output, answer in zip(outputs, answers):
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+    assert generated_text.startswith(answer)

examples/offline_inference_vision_language.py

+"""
+This example shows how to use vLLM for running offline inference 
+with the correct prompt format on vision 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.image import ImageAsset
+from vllm.assets.video import VideoAsset
+from vllm.utils import FlexibleArgumentParser
+
+
+# LLaVA-1.5
+def run_llava(question, modality):
+    assert modality == "image"
+
+    prompt = f"USER: <image>\n{question}\nASSISTANT:"
+
+    llm = LLM(model="llava-hf/llava-1.5-7b-hf")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# LLaVA-1.6/LLaVA-NeXT
+def run_llava_next(question, modality):
+    assert modality == "image"
+
+    prompt = f"[INST] <image>\n{question} [/INST]"
+    llm = LLM(model="llava-hf/llava-v1.6-mistral-7b-hf", max_model_len=8192)
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# LlaVA-NeXT-Video
+# Currently only support for video input
+def run_llava_next_video(question, modality):
+    assert modality == "video"
+
+    prompt = f"USER: <video>\n{question} ASSISTANT:"
+    llm = LLM(model="llava-hf/LLaVA-NeXT-Video-7B-hf", max_model_len=8192)
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# LLaVA-OneVision
+def run_llava_onevision(question, modality):
+
+    if modality == "video":
+        prompt = f"<|im_start|>user <video>\n{question}<|im_end|> \
+        <|im_start|>assistant\n"
+
+    elif modality == "image":
+        prompt = f"<|im_start|>user <image>\n{question}<|im_end|> \
+        <|im_start|>assistant\n"
+
+    llm = LLM(model="llava-hf/llava-onevision-qwen2-7b-ov-hf",
+              max_model_len=32768)
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# Fuyu
+def run_fuyu(question, modality):
+    assert modality == "image"
+
+    prompt = f"{question}\n"
+    llm = LLM(model="adept/fuyu-8b")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# Phi-3-Vision
+def run_phi3v(question, modality):
+    assert modality == "image"
+
+    prompt = f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n"  # noqa: E501
+    # Note: The default setting of max_num_seqs (256) and
+    # max_model_len (128k) for this model may cause OOM.
+    # You may lower either to run this example on lower-end GPUs.
+
+    # In this example, we override max_num_seqs to 5 while
+    # keeping the original context length of 128k.
+
+    # num_crops is an override kwarg to the multimodal image processor;
+    # For some models, e.g., Phi-3.5-vision-instruct, it is recommended
+    # to use 16 for single frame scenarios, and 4 for multi-frame.
+    #
+    # Generally speaking, a larger value for num_crops results in more
+    # tokens per image instance, because it may scale the image more in
+    # the image preprocessing. Some references in the model docs and the
+    # formula for image tokens after the preprocessing
+    # transform can be found below.
+    #
+    # https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
+    # https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
+    llm = LLM(
+        model="microsoft/Phi-3-vision-128k-instruct",
+        trust_remote_code=True,
+        max_num_seqs=5,
+        mm_processor_kwargs={"num_crops": 16},
+    )
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# PaliGemma
+def run_paligemma(question, modality):
+    assert modality == "image"
+
+    # PaliGemma has special prompt format for VQA
+    prompt = "caption en"
+    llm = LLM(model="google/paligemma-3b-mix-224")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# Chameleon
+def run_chameleon(question, modality):
+    assert modality == "image"
+
+    prompt = f"{question}<image>"
+    llm = LLM(model="facebook/chameleon-7b")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# MiniCPM-V
+def run_minicpmv(question, modality):
+    assert modality == "image"
+
+    # 2.0
+    # The official repo doesn't work yet, so we need to use a fork for now
+    # For more details, please see: See: https://github.com/vllm-project/vllm/pull/4087#issuecomment-2250397630 # noqa
+    # model_name = "HwwwH/MiniCPM-V-2"
+
+    # 2.5
+    # model_name = "openbmb/MiniCPM-Llama3-V-2_5"
+
+    #2.6
+    model_name = "openbmb/MiniCPM-V-2_6"
+    tokenizer = AutoTokenizer.from_pretrained(model_name,
+                                              trust_remote_code=True)
+    llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+    )
+    # NOTE The stop_token_ids are different for various versions of MiniCPM-V
+    # 2.0
+    # stop_token_ids = [tokenizer.eos_id]
+
+    # 2.5
+    # stop_token_ids = [tokenizer.eos_id, tokenizer.eot_id]
+
+    # 2.6
+    stop_tokens = ['<|im_end|>', '<|endoftext|>']
+    stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
+
+    messages = [{
+        'role': 'user',
+        'content': f'(<image>./</image>)\n{question}'
+    }]
+    prompt = tokenizer.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True)
+    return llm, prompt, stop_token_ids
+
+
+# InternVL
+def run_internvl(question, modality):
+    assert modality == "image"
+
+    model_name = "OpenGVLab/InternVL2-2B"
+
+    llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+        max_num_seqs=5,
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name,
+                                              trust_remote_code=True)
+    messages = [{'role': 'user', 'content': f"<image>\n{question}"}]
+    prompt = tokenizer.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True)
+
+    # Stop tokens for InternVL
+    # models variants may have different stop tokens
+    # please refer to the model card for the correct "stop words":
+    # https://huggingface.co/OpenGVLab/InternVL2-2B#service
+    stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
+    stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
+    return llm, prompt, stop_token_ids
+
+
+# BLIP-2
+def run_blip2(question, modality):
+    assert modality == "image"
+
+    # BLIP-2 prompt format is inaccurate on HuggingFace model repository.
+    # See https://huggingface.co/Salesforce/blip2-opt-2.7b/discussions/15#64ff02f3f8cf9e4f5b038262 #noqa
+    prompt = f"Question: {question} Answer:"
+    llm = LLM(model="Salesforce/blip2-opt-2.7b")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# Qwen
+def run_qwen_vl(question, modality):
+    assert modality == "image"
+
+    llm = LLM(
+        model="Qwen/Qwen-VL",
+        trust_remote_code=True,
+        max_num_seqs=5,
+    )
+
+    prompt = f"{question}Picture 1: <img></img>\n"
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# Qwen2-VL
+def run_qwen2_vl(question, modality):
+    assert modality == "image"
+
+    model_name = "Qwen/Qwen2-VL-7B-Instruct"
+
+    llm = LLM(
+        model=model_name,
+        max_num_seqs=5,
+    )
+
+    prompt = ("<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"
+              "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>"
+              f"{question}<|im_end|>\n"
+              "<|im_start|>assistant\n")
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# LLama
+def run_mllama(question, modality):
+    assert modality == "image"
+
+    model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+
+    # Note: The default setting of max_num_seqs (256) and
+    # max_model_len (131072) for this model may cause OOM.
+    # You may lower either to run this example on lower-end GPUs.
+
+    # The configuration below has been confirmed to launch on a
+    # single H100 GPU.
+    llm = LLM(
+        model=model_name,
+        max_num_seqs=16,
+        enforce_eager=True,
+    )
+
+    prompt = f"<|image|><|begin_of_text|>{question}"
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
+# GLM-4v
+def run_glm4v(question: str, modality: str):
+    assert modality == "image"
+    model_name = "THUDM/glm-4v-9b"
+
+    llm = LLM(model=model_name,
+              max_model_len=2048,
+              max_num_seqs=2,
+              trust_remote_code=True,
+              enforce_eager=True)
+    prompt = question
+    stop_token_ids = [151329, 151336, 151338]
+    return llm, prompt, stop_token_ids
+
+
+model_example_map = {
+    "llava": run_llava,
+    "llava-next": run_llava_next,
+    "llava-next-video": run_llava_next_video,
+    "llava-onevision": run_llava_onevision,
+    "fuyu": run_fuyu,
+    "phi3_v": run_phi3v,
+    "paligemma": run_paligemma,
+    "chameleon": run_chameleon,
+    "minicpmv": run_minicpmv,
+    "blip-2": run_blip2,
+    "internvl_chat": run_internvl,
+    "qwen_vl": run_qwen_vl,
+    "qwen2_vl": run_qwen2_vl,
+    "mllama": run_mllama,
+    "glm4v": run_glm4v,
+}
+
+
+def get_multi_modal_input(args):
+    """
+    return {
+        "data": image or video,
+        "question": question,
+    }
+    """
+    if args.modality == "image":
+        # Input image and question
+        image = ImageAsset("cherry_blossom") \
+            .pil_image.convert("RGB")
+        img_question = "What is the content of this image?"
+
+        return {
+            "data": image,
+            "question": img_question,
+        }
+
+    if args.modality == "video":
+        # Input video and question
+        video = VideoAsset(name="sample_demo_1.mp4",
+                           num_frames=args.num_frames).np_ndarrays
+        vid_question = "Why is this video funny?"
+
+        return {
+            "data": video,
+            "question": vid_question,
+        }
+
+    msg = f"Modality {args.modality} is not supported."
+    raise ValueError(msg)
+
+
+def main(args):
+    model = args.model_type
+    if model not in model_example_map:
+        raise ValueError(f"Model type {model} is not supported.")
+
+    modality = args.modality
+    mm_input = get_multi_modal_input(args)
+    data = mm_input["data"]
+    question = mm_input["question"]
+
+    llm, prompt, stop_token_ids = model_example_map[model](question, modality)
+
+    # 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
+    if args.num_prompts == 1:
+        # Single inference
+        inputs = {
+            "prompt": prompt,
+            "multi_modal_data": {
+                modality: data
+            },
+        }
+
+    else:
+        # Batch inference
+        inputs = [{
+            "prompt": prompt,
+            "multi_modal_data": {
+                modality: data
+            },
+        } for _ in range(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 '
+        'vision language models')
+    parser.add_argument('--model-type',
+                        '-m',
+                        type=str,
+                        default="llava",
+                        choices=model_example_map.keys(),
+                        help='Huggingface "model_type".')
+    parser.add_argument('--num-prompts',
+                        type=int,
+                        default=4,
+                        help='Number of prompts to run.')
+    parser.add_argument('--modality',
+                        type=str,
+                        default="image",
+                        choices=['image', 'video'],
+                        help='Modality of the input.')
+    parser.add_argument('--num-frames',
+                        type=int,
+                        default=16,
+                        help='Number of frames to extract from the video.')
+    args = parser.parse_args()
+    main(args)

examples/offline_inference_vision_language_multi_image.py

+"""
+This example shows how to use vLLM for running offline inference with
+multi-image input on vision language models, using the chat template defined
+by the model.
+"""
+from argparse import Namespace
+from typing import List, NamedTuple, Optional
+
+from PIL.Image import Image
+from transformers import AutoProcessor, AutoTokenizer
+
+from vllm import LLM, SamplingParams
+from vllm.multimodal.utils import fetch_image
+from vllm.utils import FlexibleArgumentParser
+
+QUESTION = "What is the content of each image?"
+IMAGE_URLS = [
+    "https://upload.wikimedia.org/wikipedia/commons/d/da/2015_Kaczka_krzy%C5%BCowka_w_wodzie_%28samiec%29.jpg",
+    "https://upload.wikimedia.org/wikipedia/commons/7/77/002_The_lion_king_Snyggve_in_the_Serengeti_National_Park_Photo_by_Giles_Laurent.jpg",
+]
+
+
+class ModelRequestData(NamedTuple):
+    llm: LLM
+    prompt: str
+    stop_token_ids: Optional[List[str]]
+    image_data: List[Image]
+    chat_template: Optional[str]
+
+
+def load_qwenvl_chat(question: str, image_urls: List[str]) -> ModelRequestData:
+    model_name = "Qwen/Qwen-VL-Chat"
+    llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+        max_num_seqs=5,
+        limit_mm_per_prompt={"image": len(image_urls)},
+    )
+    placeholders = "".join(f"Picture {i}: <img></img>\n"
+                           for i, _ in enumerate(image_urls, start=1))
+
+    # This model does not have a chat_template attribute on its tokenizer,
+    # so we need to explicitly pass it. We use ChatML since it's used in the
+    # generation utils of the model:
+    # https://huggingface.co/Qwen/Qwen-VL-Chat/blob/main/qwen_generation_utils.py#L265
+    tokenizer = AutoTokenizer.from_pretrained(model_name,
+                                              trust_remote_code=True)
+
+    # Copied from: https://huggingface.co/docs/transformers/main/en/chat_templating
+    chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"  # noqa: E501
+
+    messages = [{'role': 'user', 'content': f"{placeholders}\n{question}"}]
+    prompt = tokenizer.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True,
+                                           chat_template=chat_template)
+
+    stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>"]
+    stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
+    return ModelRequestData(
+        llm=llm,
+        prompt=prompt,
+        stop_token_ids=stop_token_ids,
+        image_data=[fetch_image(url) for url in image_urls],
+        chat_template=chat_template,
+    )
+
+
+def load_phi3v(question: str, image_urls: List[str]) -> ModelRequestData:
+    # num_crops is an override kwarg to the multimodal image processor;
+    # For some models, e.g., Phi-3.5-vision-instruct, it is recommended
+    # to use 16 for single frame scenarios, and 4 for multi-frame.
+    #
+    # Generally speaking, a larger value for num_crops results in more
+    # tokens per image instance, because it may scale the image more in
+    # the image preprocessing. Some references in the model docs and the
+    # formula for image tokens after the preprocessing
+    # transform can be found below.
+    #
+    # https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
+    # https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
+    llm = LLM(
+        model="microsoft/Phi-3.5-vision-instruct",
+        trust_remote_code=True,
+        max_model_len=4096,
+        limit_mm_per_prompt={"image": len(image_urls)},
+        mm_processor_kwargs={"num_crops": 4},
+    )
+    placeholders = "\n".join(f"<|image_{i}|>"
+                             for i, _ in enumerate(image_urls, start=1))
+    prompt = f"<|user|>\n{placeholders}\n{question}<|end|>\n<|assistant|>\n"
+    stop_token_ids = None
+
+    return ModelRequestData(
+        llm=llm,
+        prompt=prompt,
+        stop_token_ids=stop_token_ids,
+        image_data=[fetch_image(url) for url in image_urls],
+        chat_template=None,
+    )
+
+
+def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
+    model_name = "OpenGVLab/InternVL2-2B"
+
+    llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+        max_num_seqs=5,
+        max_model_len=4096,
+        limit_mm_per_prompt={"image": len(image_urls)},
+    )
+
+    placeholders = "\n".join(f"Image-{i}: <image>\n"
+                             for i, _ in enumerate(image_urls, start=1))
+    messages = [{'role': 'user', 'content': f"{placeholders}\n{question}"}]
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name,
+                                              trust_remote_code=True)
+    prompt = tokenizer.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True)
+
+    # Stop tokens for InternVL
+    # models variants may have different stop tokens
+    # please refer to the model card for the correct "stop words":
+    # https://huggingface.co/OpenGVLab/InternVL2-2B#service
+    stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
+    stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
+
+    return ModelRequestData(
+        llm=llm,
+        prompt=prompt,
+        stop_token_ids=stop_token_ids,
+        image_data=[fetch_image(url) for url in image_urls],
+        chat_template=None,
+    )
+
+
+def load_qwen2_vl(question, image_urls: List[str]) -> ModelRequestData:
+    try:
+        from qwen_vl_utils import process_vision_info
+    except ModuleNotFoundError:
+        print('WARNING: `qwen-vl-utils` not installed, input images will not '
+              'be automatically resized. You can enable this functionality by '
+              '`pip install qwen-vl-utils`.')
+        process_vision_info = None
+
+    model_name = "Qwen/Qwen2-VL-7B-Instruct"
+
+    llm = LLM(
+        model=model_name,
+        max_num_seqs=5,
+        max_model_len=32768 if process_vision_info is None else 4096,
+        limit_mm_per_prompt={"image": len(image_urls)},
+    )
+
+    placeholders = [{"type": "image", "image": url} for url in image_urls]
+    messages = [{
+        "role": "system",
+        "content": "You are a helpful assistant."
+    }, {
+        "role":
+        "user",
+        "content": [
+            *placeholders,
+            {
+                "type": "text",
+                "text": question
+            },
+        ],
+    }]
+
+    processor = AutoProcessor.from_pretrained(model_name)
+
+    prompt = processor.apply_chat_template(messages,
+                                           tokenize=False,
+                                           add_generation_prompt=True)
+
+    stop_token_ids = None
+
+    if process_vision_info is None:
+        image_data = [fetch_image(url) for url in image_urls]
+    else:
+        image_data, _ = process_vision_info(messages)
+
+    return ModelRequestData(
+        llm=llm,
+        prompt=prompt,
+        stop_token_ids=stop_token_ids,
+        image_data=image_data,
+        chat_template=None,
+    )
+
+
+model_example_map = {
+    "phi3_v": load_phi3v,
+    "internvl_chat": load_internvl,
+    "qwen2_vl": load_qwen2_vl,
+    "qwen_vl_chat": load_qwenvl_chat,
+}
+
+
+def run_generate(model, question: str, image_urls: List[str]):
+    req_data = model_example_map[model](question, image_urls)
+
+    sampling_params = SamplingParams(temperature=0.0,
+                                     max_tokens=128,
+                                     stop_token_ids=req_data.stop_token_ids)
+
+    outputs = req_data.llm.generate(
+        {
+            "prompt": req_data.prompt,
+            "multi_modal_data": {
+                "image": req_data.image_data
+            },
+        },
+        sampling_params=sampling_params)
+
+    for o in outputs:
+        generated_text = o.outputs[0].text
+        print(generated_text)
+
+
+def run_chat(model: str, question: str, image_urls: List[str]):
+    req_data = model_example_map[model](question, image_urls)
+
+    sampling_params = SamplingParams(temperature=0.0,
+                                     max_tokens=128,
+                                     stop_token_ids=req_data.stop_token_ids)
+    outputs = req_data.llm.chat(
+        [{
+            "role":
+            "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": question,
+                },
+                *({
+                    "type": "image_url",
+                    "image_url": {
+                        "url": image_url
+                    },
+                } for image_url in image_urls),
+            ],
+        }],
+        sampling_params=sampling_params,
+        chat_template=req_data.chat_template,
+    )
+
+    for o in outputs:
+        generated_text = o.outputs[0].text
+        print(generated_text)
+
+
+def main(args: Namespace):
+    model = args.model_type
+    method = args.method
+
+    if method == "generate":
+        run_generate(model, QUESTION, IMAGE_URLS)
+    elif method == "chat":
+        run_chat(model, QUESTION, IMAGE_URLS)
+    else:
+        raise ValueError(f"Invalid method: {method}")
+
+
+if __name__ == "__main__":
+    parser = FlexibleArgumentParser(
+        description='Demo on using vLLM for offline inference with '
+        'vision language models that support multi-image input')
+    parser.add_argument('--model-type',
+                        '-m',
+                        type=str,
+                        default="phi3_v",
+                        choices=model_example_map.keys(),
+                        help='Huggingface "model_type".')
+    parser.add_argument("--method",
+                        type=str,
+                        default="generate",
+                        choices=["generate", "chat"],
+                        help="The method to run in `vllm.LLM`.")
+
+    args = parser.parse_args()
+    main(args)

examples/offline_inference_with_profiler.py

+import os
+
+from vllm import LLM, SamplingParams
+
+# enable torch profiler, can also be set on cmd line
+os.environ["VLLM_TORCH_PROFILER_DIR"] = "./vllm_profile"
+
+# 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="facebook/opt-125m", tensor_parallel_size=1)
+
+llm.start_profile()
+
+# 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)
+
+llm.stop_profile()
+
+# 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/openai_audio_api_client.py

+"""An example showing how to use vLLM to serve VLMs.
+
+Launch the vLLM server with the following command:
+vllm serve fixie-ai/ultravox-v0_3
+"""
+import base64
+
+import requests
+from openai import OpenAI
+
+from vllm.assets.audio import AudioAsset
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+# Any format supported by librosa is supported
+audio_url = AudioAsset("winning_call").url
+
+# Use audio url in the payload
+chat_completion_from_url = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this audio?"
+            },
+            {
+                "type": "audio_url",
+                "audio_url": {
+                    "url": audio_url
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_tokens=64,
+)
+
+result = chat_completion_from_url.choices[0].message.content
+print(f"Chat completion output:{result}")
+
+
+# Use base64 encoded audio in the payload
+def encode_audio_base64_from_url(audio_url: str) -> str:
+    """Encode an audio retrieved from a remote url to base64 format."""
+
+    with requests.get(audio_url) as response:
+        response.raise_for_status()
+        result = base64.b64encode(response.content).decode('utf-8')
+
+    return result
+
+
+audio_base64 = encode_audio_base64_from_url(audio_url=audio_url)
+chat_completion_from_base64 = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this audio?"
+            },
+            {
+                "type": "audio_url",
+                "audio_url": {
+                    # Any format supported by librosa is supported
+                    "url": f"data:audio/ogg;base64,{audio_base64}"
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_tokens=64,
+)
+
+result = chat_completion_from_base64.choices[0].message.content
+print(f"Chat completion output:{result}")

examples/openai_chat_completion_client_with_tools.py

+"""
+Set up this example by starting a vLLM OpenAI-compatible server with tool call
+options enabled. For example:
+
+IMPORTANT: for mistral, you must use one of the provided mistral tool call
+templates, or your own - the model default doesn't work for tool calls with vLLM
+See the vLLM docs on OpenAI server & tool calling for more details.
+
+vllm serve --model mistralai/Mistral-7B-Instruct-v0.3 \
+            --chat-template examples/tool_chat_template_mistral.jinja \
+            --enable-auto-tool-choice --tool-call-parser mistral
+
+OR
+vllm serve --model NousResearch/Hermes-2-Pro-Llama-3-8B \
+            --chat-template examples/tool_chat_template_hermes.jinja \
+            --enable-auto-tool-choice --tool-call-parser hermes
+"""
+import json
+
+from openai import OpenAI
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+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": "Hi! How are you doing today?"
+}, {
+    "role": "assistant",
+    "content": "I'm doing well! How can I help you?"
+}, {
+    "role":
+    "user",
+    "content":
+    "Can you tell me what the temperate will be in Dallas, in fahrenheit?"
+}]
+
+chat_completion = client.chat.completions.create(messages=messages,
+                                                 model=model,
+                                                 tools=tools)
+
+print("Chat completion results:")
+print(chat_completion)
+print("\n\n")
+
+tool_calls_stream = client.chat.completions.create(messages=messages,
+                                                   model=model,
+                                                   tools=tools,
+                                                   stream=True)
+
+chunks = []
+for chunk in tool_calls_stream:
+    chunks.append(chunk)
+    if chunk.choices[0].delta.tool_calls:
+        print(chunk.choices[0].delta.tool_calls[0])
+    else:
+        print(chunk.choices[0].delta)
+
+arguments = []
+tool_call_idx = -1
+for chunk in chunks:
+
+    if chunk.choices[0].delta.tool_calls:
+        tool_call = chunk.choices[0].delta.tool_calls[0]
+
+        if tool_call.index != tool_call_idx:
+            if tool_call_idx >= 0:
+                print(
+                    f"streamed tool call arguments: {arguments[tool_call_idx]}"
+                )
+            tool_call_idx = chunk.choices[0].delta.tool_calls[0].index
+            arguments.append("")
+        if tool_call.id:
+            print(f"streamed tool call id: {tool_call.id} ")
+
+        if tool_call.function:
+            if tool_call.function.name:
+                print(f"streamed tool call name: {tool_call.function.name}")
+
+            if tool_call.function.arguments:
+                arguments[tool_call_idx] += tool_call.function.arguments
+
+if len(arguments):
+    print(f"streamed tool call arguments: {arguments[-1]}")
+
+print("\n\n")
+
+messages.append({
+    "role": "assistant",
+    "tool_calls": chat_completion.choices[0].message.tool_calls
+})
+
+
+# Now, simulate a tool call
+def get_current_weather(city: str, state: str, unit: 'str'):
+    return ("The weather in Dallas, Texas is 85 degrees fahrenheit. It is "
+            "partly cloudly, with highs in the 90's.")
+
+
+available_tools = {"get_current_weather": get_current_weather}
+
+completion_tool_calls = chat_completion.choices[0].message.tool_calls
+for call in completion_tool_calls:
+    tool_to_call = available_tools[call.function.name]
+    args = json.loads(call.function.arguments)
+    result = tool_to_call(**args)
+    print(result)
+    messages.append({
+        "role": "tool",
+        "content": result,
+        "tool_call_id": call.id,
+        "name": call.function.name
+    })
+
+chat_completion_2 = client.chat.completions.create(messages=messages,
+                                                   model=model,
+                                                   tools=tools,
+                                                   stream=False)
+print("\n\n")
+print(chat_completion_2)

examples/openai_vision_api_client.py

+"""An example showing how to use vLLM to serve VLMs.
+
+Launch the vLLM server with the following command:
+
+(single image inference with Llava)
+vllm serve llava-hf/llava-1.5-7b-hf --chat-template template_llava.jinja
+
+(multi-image inference with Phi-3.5-vision-instruct)
+vllm serve microsoft/Phi-3.5-vision-instruct --max-model-len 4096 \
+    --trust-remote-code --limit-mm-per-prompt image=2
+"""
+import base64
+
+import requests
+from openai import OpenAI
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+# Single-image input inference
+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"
+
+## Use image url in the payload
+chat_completion_from_url = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this image?"
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_tokens=64,
+)
+
+result = chat_completion_from_url.choices[0].message.content
+print("Chat completion output:", result)
+
+
+## Use base64 encoded image in the payload
+def encode_image_base64_from_url(image_url: str) -> str:
+    """Encode an image retrieved from a remote url to base64 format."""
+
+    with requests.get(image_url) as response:
+        response.raise_for_status()
+        result = base64.b64encode(response.content).decode('utf-8')
+
+    return result
+
+
+image_base64 = encode_image_base64_from_url(image_url=image_url)
+chat_completion_from_base64 = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this image?"
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:image/jpeg;base64,{image_base64}"
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_tokens=64,
+)
+
+result = chat_completion_from_base64.choices[0].message.content
+print(f"Chat completion output:{result}")
+
+# Multi-image input inference
+image_url_duck = "https://upload.wikimedia.org/wikipedia/commons/d/da/2015_Kaczka_krzy%C5%BCowka_w_wodzie_%28samiec%29.jpg"
+image_url_lion = "https://upload.wikimedia.org/wikipedia/commons/7/77/002_The_lion_king_Snyggve_in_the_Serengeti_National_Park_Photo_by_Giles_Laurent.jpg"
+chat_completion_from_url = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What are the animals in these images?"
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url_duck
+                },
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url_lion
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_tokens=64,
+)
+
+result = chat_completion_from_url.choices[0].message.content
+print("Chat completion output:", result)

examples/production_monitoring/Otel.md

+# Setup OpenTelemetry POC
+
+1. Install OpenTelemetry packages:
+    ```
+    pip install \
+      'opentelemetry-sdk>=1.26.0,<1.27.0' \
+      'opentelemetry-api>=1.26.0,<1.27.0' \
+      'opentelemetry-exporter-otlp>=1.26.0,<1.27.0' \
+      'opentelemetry-semantic-conventions-ai>=0.4.1,<0.5.0'
+    ```
+
+1. Start Jaeger in a docker container:
+    ```
+    # From: https://www.jaegertracing.io/docs/1.57/getting-started/
+    docker run --rm --name jaeger \
+        -e COLLECTOR_ZIPKIN_HOST_PORT=:9411 \
+        -p 6831:6831/udp \
+        -p 6832:6832/udp \
+        -p 5778:5778 \
+        -p 16686:16686 \
+        -p 4317:4317 \
+        -p 4318:4318 \
+        -p 14250:14250 \
+        -p 14268:14268 \
+        -p 14269:14269 \
+        -p 9411:9411 \
+        jaegertracing/all-in-one:1.57
+    ```
+
+1. In a new shell, export Jaeger IP:
+    ```
+    export JAEGER_IP=$(docker inspect   --format '{{ .NetworkSettings.IPAddress }}' jaeger)
+    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+    ```
+    Then set vLLM's service name for OpenTelemetry, enable insecure connections to Jaeger and run vLLM:
+    ```
+    export OTEL_SERVICE_NAME="vllm-server"
+    export OTEL_EXPORTER_OTLP_TRACES_INSECURE=true
+    vllm serve facebook/opt-125m --otlp-traces-endpoint="$OTEL_EXPORTER_OTLP_TRACES_ENDPOINT"
+    ```
+
+1. In a new shell, send requests with trace context from a dummy client
+    ```
+    export JAEGER_IP=$(docker inspect --format '{{ .NetworkSettings.IPAddress }}' jaeger)
+    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+    export OTEL_EXPORTER_OTLP_TRACES_INSECURE=true
+    export OTEL_SERVICE_NAME="client-service"
+    python dummy_client.py
+    ```
+
+1. Open Jaeger webui: http://localhost:16686/
+
+    In the search pane, select `vllm-server` service and hit `Find Traces`. You should get a list of traces, one for each request.
+    ![Traces](https://i.imgur.com/GYHhFjo.png)
+
+1. Clicking on a trace will show its spans and their tags. In this demo, each trace has 2 spans. One from the dummy client containing the prompt text and one from vLLM containing metadata about the request.
+![Spans details](https://i.imgur.com/OPf6CBL.png)
+
+## Exporter Protocol
+OpenTelemetry supports either `grpc` or `http/protobuf` as the transport protocol for trace data in the exporter.
+By default, `grpc` is used. To set `http/protobuf` as the protocol, configure the `OTEL_EXPORTER_OTLP_TRACES_PROTOCOL` environment variable as follows:
+```
+export OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf
+export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
+vllm serve facebook/opt-125m --otlp-traces-endpoint="$OTEL_EXPORTER_OTLP_TRACES_ENDPOINT"
+```
+
+## Instrumentation of FastAPI
+OpenTelemetry allows automatic instrumentation of FastAPI.
+1. Install the instrumentation library
+    ```
+    pip install opentelemetry-instrumentation-fastapi
+    ```
+
+1. Run vLLM with `opentelemetry-instrument`
+    ```
+    opentelemetry-instrument vllm serve facebook/opt-125m
+    ```
+
+1. Send a request to vLLM and find its trace in Jaeger. It should contain spans from FastAPI.
+
+![FastAPI Spans](https://i.imgur.com/hywvoOJ.png)
\ No newline at end of file

examples/production_monitoring/dummy_client.py

+import requests
+from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import (
+    OTLPSpanExporter)
+from opentelemetry.sdk.trace import TracerProvider
+from opentelemetry.sdk.trace.export import (BatchSpanProcessor,
+                                            ConsoleSpanExporter)
+from opentelemetry.trace import SpanKind, set_tracer_provider
+from opentelemetry.trace.propagation.tracecontext import (
+    TraceContextTextMapPropagator)
+
+trace_provider = TracerProvider()
+set_tracer_provider(trace_provider)
+
+trace_provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
+trace_provider.add_span_processor(BatchSpanProcessor(ConsoleSpanExporter()))
+
+tracer = trace_provider.get_tracer("dummy-client")
+
+url = "http://localhost:8000/v1/completions"
+with tracer.start_as_current_span("client-span", kind=SpanKind.CLIENT) as span:
+    prompt = "San Francisco is a"
+    span.set_attribute("prompt", prompt)
+    headers = {}
+    TraceContextTextMapPropagator().inject(headers)
+    payload = {
+        "model": "facebook/opt-125m",
+        "prompt": prompt,
+        "max_tokens": 10,
+        "best_of": 20,
+        "n": 3,
+        "use_beam_search": "true",
+        "temperature": 0.0,
+        # "stream": True,
+    }
+    response = requests.post(url, headers=headers, json=payload)

examples/run_cluster.sh

+#!/bin/bash
+
+# Check for minimum number of required arguments
+if [ $# -lt 4 ]; then
+    echo "Usage: $0 docker_image head_node_address --head|--worker path_to_hf_home [additional_args...]"
+    exit 1
+fi
+
+# Assign the first three arguments and shift them away
+DOCKER_IMAGE="$1"
+HEAD_NODE_ADDRESS="$2"
+NODE_TYPE="$3"  # Should be --head or --worker
+PATH_TO_HF_HOME="$4"
+shift 4
+
+# Additional arguments are passed directly to the Docker command
+ADDITIONAL_ARGS="$@"
+
+# Validate node type
+if [ "${NODE_TYPE}" != "--head" ] && [ "${NODE_TYPE}" != "--worker" ]; then
+    echo "Error: Node type must be --head or --worker"
+    exit 1
+fi
+
+# Define a function to cleanup on EXIT signal
+cleanup() {
+    docker stop node
+    docker rm node
+}
+trap cleanup EXIT
+
+# Command setup for head or worker node
+RAY_START_CMD="ray start --block"
+if [ "${NODE_TYPE}" == "--head" ]; then
+    RAY_START_CMD+=" --head --port=6379"
+else
+    RAY_START_CMD+=" --address=${HEAD_NODE_ADDRESS}:6379"
+fi
+
+# Run the docker command with the user specified parameters and additional arguments
+docker run \
+    --entrypoint /bin/bash \
+    --network host \
+    --name node \
+    --shm-size 10.24g \
+    --gpus all \
+    -v "${PATH_TO_HF_HOME}:/root/.cache/huggingface" \
+    ${ADDITIONAL_ARGS} \
+    "${DOCKER_IMAGE}" -c "${RAY_START_CMD}"

examples/template_blip2.jinja

+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- 'Question: ' + message['content'] + ' ' -}}
+    {%- elif message['role'] == 'assistant' -%}
+        {{- 'Answer: ' + message['content'] + ' ' -}}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{- 'Answer:' -}}
+{% endif %}

examples/template_chatglm2.jinja

+{%- set counter = namespace(index=1) -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- '[Round ' + counter.index|string + ']\n\n问：' + message['content'] -}}
+        {%- set counter.index = counter.index + 1 -%}
+    {%- endif -%}
+    {%- if message['role'] == 'assistant' -%}
+        {{- '\n\n答：' + message['content'] -}}
+        {%- if (loop.last and add_generation_prompt) or not loop.last -%}
+            {{- '\n\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+
+{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
+    {{- '\n\n答：' -}}
+{%- endif -%}
\ No newline at end of file

examples/template_telechat.jinja

+{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}
+
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- '<_user>' + message['content'] +'<_bot>' -}}
+    {%- elif message['role'] == 'assistant' -%}
+        {{- message['content'] + '<_end>' -}}
+    {%- endif -%}
+{%- endfor -%}

examples/tool_chat_template_hermes.jinja

+{%- macro json_to_python_type(json_spec) %}
+    {%- set basic_type_map = {
+    "string": "str",
+    "number": "float",
+    "integer": "int",
+    "boolean": "bool"
+} %}
+
+    {%- if basic_type_map[json_spec.type] is defined %}
+        {{- basic_type_map[json_spec.type] }}
+    {%- elif json_spec.type == "array" %}
+        {{- "list[" +  json_to_python_type(json_spec|items) + "]" }}
+    {%- elif json_spec.type == "object" %}
+        {%- if json_spec.additionalProperties is defined %}
+            {{- "dict[str, " + json_to_python_type(json_spec.additionalProperties) + ']' }}
+        {%- else %}
+            {{- "dict" }}
+        {%- endif %}
+    {%- elif json_spec.type is iterable %}
+        {{- "Union[" }}
+        {%- for t in json_spec.type %}
+            {{- json_to_python_type({"type": t}) }}
+            {%- if not loop.last %}
+                {{- "," }}
+            {%- endif %}
+        {%- endfor %}
+        {{- "]" }}
+    {%- else %}
+        {{- "Any" }}
+    {%- endif %}
+{%- endmacro %}
+
+
+{{- bos_token }}
+{{- "<|im_start|>system\nYou are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> " }}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- '{"type": "function", "function": ' }}
+        {{- '{"name": "' + tool.name + '", ' }}
+        {{- '"description": "' + tool.name + '(' }}
+        {%- for param_name, param_fields in tool.parameters.properties|items %}
+            {{- param_name + ": " + json_to_python_type(param_fields) }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- endif %}
+        {%- endfor %}
+        {{- ")" }}
+        {%- if tool.return is defined %}
+            {{- " -> " + json_to_python_type(tool.return) }}
+        {%- endif %}
+        {{- " - " + tool.description + "\n\n" }}
+        {%- for param_name, param_fields in tool.parameters.properties|items %}
+            {%- if loop.first %}
+                {{- "    Args:\n" }}
+            {%- endif %}
+            {{- "        " + param_name + "(" + json_to_python_type(param_fields) + "): " + param_fields.description|trim }}
+        {%- endfor %}
+        {%- if tool.return is defined and tool.return.description is defined %}
+            {{- "\n    Returns:\n        " + tool.return.description }}
+        {%- endif %}
+        {{- '"' }}
+        {{- ', "parameters": ' }}
+        {%- if tool.parameters.properties | length == 0 %}
+            {{- "{}" }}
+        {%- else %}
+            {{- tool.parameters|tojson }}
+        {%- endif %}
+        {{- "}" }}
+        {%- if not loop.last %}
+            {{- "\n" }}
+        {%- endif %}
+    {%- endfor %}
+{%- endif %}
+{{- " </tools>" }}
+{{- 'Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
+' }}
+{{- "For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+" }}
+{{- "<tool_call>
+" }}
+{{- '{"name": <function-name>, "arguments": <args-dict>}
+' }}
+{{- '</tool_call><|im_end|>' }}
+{%- for message in messages %}
+    {%- if message.role == "user" or message.role == "system" or (message.role == "assistant" and message.tool_calls is not defined) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" and message.tool_calls is defined %}
+        {{- '<|im_start|>' + message.role }}
+        {%- for tool_call in message.tool_calls %}
+            {{- '\n<tool_call>\n' }}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '{' }}
+            {{- '"name": "' }}
+            {{- tool_call.name }}
+            {{- '"' }}
+            {%- if tool_call.arguments is defined %}
+                {{- ', ' }}
+                {{- '"arguments": ' }}
+                {{- tool_call.arguments|tojson }}
+            {%- endif %}
+            {{- '}' }}
+            {{- '\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>tool\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {%- if not loop.last %}
+            {{- '\n</tool_response>\n' }}
+        {%- else %}
+            {{- '\n</tool_response>' }}
+        {%- endif %}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

examples/tool_chat_template_mistral.jinja

+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{%- for message in loop_messages | rejectattr("role", "equalto", "tool") | rejectattr("role", "equalto", "tool_results") | selectattr("tool_calls", "undefined") %}
+    {%- if (message["role"] == "user") != (loop.index0 % 2 == 0) %}
+        {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+        {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message["role"] == "tool_calls" or message.tool_calls is defined %}
+        {%- if message.tool_calls is defined %}
+            {%- set tool_calls = message.tool_calls %}
+        {%- else %}
+            {%- set tool_calls = message.content %}
+        {%- endif %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length < 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (1)" + tool_call.id) }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id[-9:] + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"] + eos_token }}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length < 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (2)" + message.tool_call_id) }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id[-9:] + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}