No commit message

No commit message

examples/offline_inference_arctic.py

+from vllm import LLM, SamplingParams
+
+# 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="snowflake/snowflake-arctic-instruct",
+          quantization="deepspeedfp",
+          tensor_parallel_size=8,
+          trust_remote_code=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_distributed.py

+"""
+This example shows how to use Ray Data for running offline batch inference
+distributively on a multi-nodes cluster.
+
+Learn more about Ray Data in https://docs.ray.io/en/latest/data/data.html
+"""
+
+from typing import Dict
+
+import numpy as np
+import ray
+from packaging.version import Version
+from ray.util.scheduling_strategies import PlacementGroupSchedulingStrategy
+
+from vllm import LLM, SamplingParams
+
+assert Version(ray.__version__) >= Version(
+    "2.22.0"), "Ray version must be at least 2.22.0"
+
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+# Set tensor parallelism per instance.
+tensor_parallel_size = 1
+
+# Set number of instances. Each instance will use tensor_parallel_size GPUs.
+num_instances = 1
+
+
+# Create a class to do batch inference.
+class LLMPredictor:
+
+    def __init__(self):
+        # Create an LLM.
+        self.llm = LLM(model="meta-llama/Llama-2-7b-chat-hf",
+                       tensor_parallel_size=tensor_parallel_size)
+
+    def __call__(self, batch: Dict[str, np.ndarray]) -> Dict[str, list]:
+        # Generate texts from the prompts.
+        # The output is a list of RequestOutput objects that contain the prompt,
+        # generated text, and other information.
+        outputs = self.llm.generate(batch["text"], sampling_params)
+        prompt = []
+        generated_text = []
+        for output in outputs:
+            prompt.append(output.prompt)
+            generated_text.append(' '.join([o.text for o in output.outputs]))
+        return {
+            "prompt": prompt,
+            "generated_text": generated_text,
+        }
+
+
+# Read one text file from S3. Ray Data supports reading multiple files
+# from cloud storage (such as JSONL, Parquet, CSV, binary format).
+ds = ray.data.read_text("s3://anonymous@air-example-data/prompts.txt")
+
+
+# For tensor_parallel_size > 1, we need to create placement groups for vLLM
+# to use. Every actor has to have its own placement group.
+def scheduling_strategy_fn():
+    # One bundle per tensor parallel worker
+    pg = ray.util.placement_group(
+        [{
+            "GPU": 1,
+            "CPU": 1
+        }] * tensor_parallel_size,
+        strategy="STRICT_PACK",
+    )
+    return dict(scheduling_strategy=PlacementGroupSchedulingStrategy(
+        pg, placement_group_capture_child_tasks=True))
+
+
+resources_kwarg = {}
+if tensor_parallel_size == 1:
+    # For tensor_parallel_size == 1, we simply set num_gpus=1.
+    resources_kwarg["num_gpus"] = 1
+else:
+    # Otherwise, we have to set num_gpus=0 and provide
+    # a function that will create a placement group for
+    # each instance.
+    resources_kwarg["num_gpus"] = 0
+    resources_kwarg["ray_remote_args_fn"] = scheduling_strategy_fn
+
+# Apply batch inference for all input data.
+ds = ds.map_batches(
+    LLMPredictor,
+    # Set the concurrency to the number of LLM instances.
+    concurrency=num_instances,
+    # Specify the batch size for inference.
+    batch_size=32,
+    **resources_kwarg,
+)
+
+# Peek first 10 results.
+# NOTE: This is for local testing and debugging. For production use case,
+# one should write full result out as shown below.
+outputs = ds.take(limit=10)
+for output in outputs:
+    prompt = output["prompt"]
+    generated_text = output["generated_text"]
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+# Write inference output data out as Parquet files to S3.
+# Multiple files would be written to the output destination,
+# and each task would write one or more files separately.
+#
+# ds.write_parquet("s3://<your-output-bucket>")

examples/offline_inference_embedding.py

+from vllm import LLM
+
+# 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 an LLM.
+model = LLM(model="intfloat/e5-mistral-7b-instruct", enforce_eager=True)
+# Generate embedding. The output is a list of EmbeddingRequestOutputs.
+outputs = model.encode(prompts)
+# Print the outputs.
+for output in outputs:
+    print(output.outputs.embedding)  # list of 4096 floats

examples/offline_inference_neuron.py

+from vllm import LLM, SamplingParams
+
+# 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=128,
+    block_size=128,
+    # 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",
+    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

+# Offline Inference with the OpenAI Batch file format
+
+ **NOTE:** This is a guide to performing batch inference using the OpenAI batch file format, **NOT** the complete Batch (REST) API.
+ 
+ ## File Format
+ 
+ The OpenAI batch file format consists of a series of json objects on new lines.
+ 
+ [See here for an example file.](https://github.com/vllm-project/vllm/blob/main/examples/openai_example_batch.jsonl)
+ 
+ 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).
+ 
+ ## Pre-requisites
+ 
+* Ensure you are using `vllm >= 0.4.3`. You can check by running `python -c "import vllm; print(vllm.__version__)"`.
+* The examples in this document use `meta-llama/Meta-Llama-3-8B-Instruct`.
+  - Create a [user access token](https://huggingface.co/docs/hub/en/security-tokens)
+  - Install the token on your machine (Run `huggingface-cli login`).
+  - 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
+ 
+ ### Step 1: Create your batch file
+ 
+ To follow along with this example, you can download the example batch, or create your own batch file in your working directory.
+ 
+ ```
+ wget https://raw.githubusercontent.com/vllm-project/vllm/main/examples/openai_example_batch.jsonl
+ ```
+ 
+ Once you've created your batch file it should look like this
+ 
+ ```
+ $ cat openai_example_batch.jsonl
+{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+ ```
+ 
+ ### Step 2: Run the batch
+ 
+The batch running tool is designed to be used from the command line.
+
+You can run the batch with the following command, which will write its results to a file called `results.jsonl`
+
+```
+python -m vllm.entrypoints.openai.run_batch -i openai_example_batch.jsonl -o results.jsonl --model meta-llama/Meta-Llama-3-8B-Instruct
+```
+
+### Step 3: Check your results
+
+You should now have your results at `results.jsonl`. You can check your results by running `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}
+```
+
+## Example 2: Using remote files
+
+The batch runner supports remote input and output urls that are accessible via http/https.
+
+For example, to run against our example input file located at `https://raw.githubusercontent.com/vllm-project/vllm/main/examples/openai_example_batch.jsonl`, you can run
+
+```
+python -m vllm.entrypoints.openai.run_batch -i https://raw.githubusercontent.com/vllm-project/vllm/main/examples/openai_example_batch.jsonl -o results.jsonl --model meta-llama/Meta-Llama-3-8B-Instruct
+```
+
+## Example 3: Integrating with AWS S3
+
+To integrate with cloud blob storage, we recommend using presigned urls.
+
+[Learn more about S3 presigned urls here]
+
+### Additional prerequisites
+
+* [Create an S3 bucket](https://docs.aws.amazon.com/AmazonS3/latest/userguide/creating-bucket.html). 
+* The `awscli` package (Run `pip install awscli`) to configure your credentials and interactively use s3.
+  - [Configure your credentials](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-quickstart.html).
+* The `boto3` python package (Run `pip install boto3`) to generate presigned urls.
+
+### Step 1: Upload your input script
+
+To follow along with this example, you can download the example batch, or create your own batch file in your working directory.
+ 
+ ```
+ wget https://raw.githubusercontent.com/vllm-project/vllm/main/examples/openai_example_batch.jsonl
+ ```
+ 
+ Once you've created your batch file it should look like this
+ 
+ ```
+ $ cat openai_example_batch.jsonl
+{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+ ```
+
+Now upload your batch file to your S3 bucket.
+
+```
+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.
+
+(The script is adapted from https://github.com/awsdocs/aws-doc-sdk-examples/blob/main/python/example_code/s3/s3_basics/presigned_url.py)
+
+```
+import boto3
+from botocore.exceptions import ClientError
+
+def generate_presigned_url(s3_client, client_method, method_parameters, expires_in):
+    """
+    Generate a presigned Amazon S3 URL that can be used to perform an action.
+
+    :param s3_client: A Boto3 Amazon S3 client.
+    :param client_method: The name of the client method that the URL performs.
+    :param method_parameters: The parameters of the specified client method.
+    :param expires_in: The number of seconds the presigned URL is valid for.
+    :return: The presigned URL.
+    """
+    try:
+        url = s3_client.generate_presigned_url(
+            ClientMethod=client_method, Params=method_parameters, ExpiresIn=expires_in
+        )
+    except ClientError:
+        raise
+    return url
+
+
+s3_client = boto3.client("s3")
+input_url = generate_presigned_url(
+    s3_client, "get_object", {"Bucket": "MY_BUCKET", "Key": "MY_INPUT_FILE.jsonl"}, 3600
+)
+output_url = generate_presigned_url(
+    s3_client, "put_object", {"Bucket": "MY_BUCKET", "Key": "MY_OUTPUT_FILE.jsonl"}, 3600
+)
+print(f"{input_url=}")
+print(f"{output_url=}")
+```
+
+This script should output
+
+```
+input_url='https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_INPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091'
+output_url='https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_OUTPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091'
+```
+
+### Step 3: Run the batch runner using your presigned urls
+
+You can now run the batch runner, using the urls generated in the previous section.
+
+```
+python -m vllm.entrypoints.openai.run_batch \
+    -i "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_INPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
+    -o "https://s3.us-west-2.amazonaws.com/MY_BUCKET/MY_OUTPUT_FILE.jsonl?AWSAccessKeyId=ABCDEFGHIJKLMNOPQRST&Signature=abcdefghijklmnopqrstuvwxyz12345&Expires=1715800091" \
+    --model --model meta-llama/Meta-Llama-3-8B-Instruct
+```
+
+### Step 4: View your results
+
+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 -
+```

examples/offline_inference_with_prefix.py

+from time import time
+
+from vllm import LLM, SamplingParams
+
+# Common prefix.
+prefix = (
+    "You are an expert school principal, skilled in effectively managing "
+    "faculty and staff. Draft 10-15 questions for a potential first grade "
+    "Head Teacher for my K-12, all-girls', independent school that emphasizes "
+    "community, joyful discovery, and life-long learning. The candidate is "
+    "coming in for a first-round panel interview for a 8th grade Math "
+    "teaching role. They have 5 years of previous teaching experience "
+    "as an assistant teacher at a co-ed, public school with experience "
+    "in middle school math teaching. Based on these information, fulfill "
+    "the following paragraph: ")
+
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+
+generating_prompts = [prefix + prompt for prompt in prompts]
+
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.0)
+
+# Create an LLM.
+regular_llm = LLM(model="facebook/opt-125m", gpu_memory_utilization=0.4)
+
+prefix_cached_llm = LLM(model="facebook/opt-125m",
+                        enable_prefix_caching=True,
+                        gpu_memory_utilization=0.4)
+print("Results without `enable_prefix_caching`")
+
+# Generate texts from the prompts. The output is a list of RequestOutput objects
+# that contain the prompt, generated text, and other information.
+start_time_regular = time()
+outputs = regular_llm.generate(generating_prompts, sampling_params)
+duration_regular = time() - start_time_regular
+
+regular_generated_texts = []
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    regular_generated_texts.append(generated_text)
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+print("-" * 80)
+
+# Warmup so that the shared prompt's KV cache is computed.
+prefix_cached_llm.generate(generating_prompts[0], sampling_params)
+
+# Generate with prefix caching.
+start_time_cached = time()
+outputs = prefix_cached_llm.generate(generating_prompts, sampling_params)
+duration_cached = time() - start_time_cached
+
+print("Results with `enable_prefix_caching`")
+
+cached_generated_texts = []
+# Print the outputs. You should see the same outputs as before.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    cached_generated_texts.append(generated_text)
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+print("-" * 80)
+
+# Compare the results and display the speedup
+generated_same = all([
+    regular_generated_texts[i] == cached_generated_texts[i]
+    for i in range(len(prompts))
+])
+print(f"Generated answers are the same: {generated_same}")
+
+speedup = round(duration_regular / duration_cached, 2)
+print(f"Speed up of cached generation compared to the regular is: {speedup}")

examples/offline_streaming_inference_chat_demo.py

+from vllm.sampling_params import SamplingParams
+from vllm.engine.async_llm_engine import AsyncEngineArgs, AsyncLLMEngine
+import asyncio
+from vllm.utils import FlexibleArgumentParser
+from transformers import AutoTokenizer
+import logging
+import argparse
+import sys
+vllm_logger = logging.getLogger("vllm")
+vllm_logger.setLevel(logging.WARNING)
+
+class FlexibleArgumentParser(argparse.ArgumentParser):
+    """ArgumentParser that allows both underscore and dash in names."""
+
+    def parse_args(self, args=None, namespace=None):
+        if args is None:
+            args = sys.argv[1:]
+
+        # Convert underscores to dashes and vice versa in argument names
+        processed_args = []
+        for arg in args:
+            if arg.startswith('--'):
+                if '=' in arg:
+                    key, value = arg.split('=', 1)
+                    key = '--' + key[len('--'):].replace('_', '-')
+                    processed_args.append(f'{key}={value}')
+                else:
+                    processed_args.append('--' +
+                                          arg[len('--'):].replace('_', '-'))
+            else:
+                processed_args.append(arg)
+
+        return super().parse_args(processed_args, namespace)
+   
+parser = FlexibleArgumentParser()
+parser.add_argument('--template', type=str, help="Path to template")
+parser = AsyncEngineArgs.add_cli_args(parser)
+args = parser.parse_args()
+
+# chat = [
+#   {"role": "user", "content": "Hello, how are you?"},
+#   {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
+#   {"role": "user", "content": "I'd like to show off how chat templating works!"},
+# ]
+
+tokenizer =  AutoTokenizer.from_pretrained(args.model)
+try:
+     f = open(args.template,'r')
+     tokenizer.chat_template = f.read()
+except Exception as e:
+     print('except:',e)
+finally:
+     f.close()
+
+
+
+engine_args = AsyncEngineArgs.from_cli_args(args)
+engine = AsyncLLMEngine.from_engine_args(engine_args)
+
+
+model_name = args.model.split("/")[-1] if args.model.split("/")[-1] !=""  else args.model.split("/")[-2]
+print(f"欢迎使用{model_name}模型,输入内容即可进行对话,stop 终止程序")
+
+
+def build_prompt(history):
+    prompt = ""
+    for query, response in history:
+        prompt += f"\n\n用户:{query}"
+        prompt += f"\n\n{model_name}:{response}"
+    return prompt
+
+
+history = []
+while True:
+     query = input("\n用户:")
+     if query.strip() == "stop":
+          break 
+     history.append({"role": "user", "content": query})
+     new_query = tokenizer.apply_chat_template(history, tokenize=False)
+     example_input = {
+     "prompt": new_query,
+     "stream": False, 
+     "temperature": 0.0,
+     "request_id": 0,
+     }
+
+     results_generator = engine.generate(
+     example_input["prompt"],
+     SamplingParams(temperature=example_input["temperature"], max_tokens=100),
+     example_input["request_id"]
+     )
+
+     start = 0
+     end = 0
+     response = ""
+     async def process_results():
+          async for  output in results_generator: 
+               global end 
+               global start 
+               global response
+               print(output.outputs[0].text[start:], end="", flush=True)
+               length = len(output.outputs[0].text)
+               start = length
+               response = output.outputs[0].text
+     
+     asyncio.run(process_results())
+     history.append({"role": "assistant", "content": response})
+print()
+
+

examples/openai_chat_completion_client.py

+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
+
+chat_completion = client.chat.completions.create(
+    messages=[{
+        "role": "system",
+        "content": "You are a helpful assistant."
+    }, {
+        "role": "user",
+        "content": "Who won the world series in 2020?"
+    }, {
+        "role":
+        "assistant",
+        "content":
+        "The Los Angeles Dodgers won the World Series in 2020."
+    }, {
+        "role": "user",
+        "content": "Where was it played?"
+    }],
+    model=model,
+)
+
+print("Chat completion results:")
+print(chat_completion)

examples/openai_completion_client.py

+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
+
+# Completion API
+stream = False
+completion = client.completions.create(
+    model=model,
+    prompt="A robot may not injure a human being",
+    echo=False,
+    n=2,
+    stream=stream,
+    logprobs=3)
+
+print("Completion results:")
+if stream:
+    for c in completion:
+        print(c)
+else:
+    print(completion)

examples/openai_embedding_client.py

+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
+
+responses = client.embeddings.create(input=[
+    "Hello my name is",
+    "The best thing about vLLM is that it supports many different models"
+],
+                                     model=model)
+
+for data in responses.data:
+    print(data.embedding)  # list of float of len 4096

examples/openai_example_batch.jsonl

+{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}

examples/production_monitoring/README.md

+# vLLM + Prometheus/Grafana 
+
+This is a simple example that shows you how to connect vLLM metric logging to the Prometheus/Grafana stack. For this example, we launch Prometheus and Grafana via Docker. You can checkout other methods through [Prometheus](https://prometheus.io/) and [Grafana](https://grafana.com/) websites. 
+
+Install: 
+- [`docker`](https://docs.docker.com/engine/install/)
+- [`docker compose`](https://docs.docker.com/compose/install/linux/#install-using-the-repository)
+
+### Launch
+
+Prometheus metric logging is enabled by default in the OpenAI-compatible server. Launch via the entrypoint:
+```bash
+python3 -m vllm.entrypoints.openai.api_server \
+    --model mistralai/Mistral-7B-v0.1 \
+    --max-model-len 2048 \
+    --disable-log-requests
+```
+
+Launch Prometheus and Grafana servers with `docker compose`:
+```bash
+docker compose up
+```
+
+Submit some sample requests to the server:
+```bash
+wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
+
+python3 ../../benchmarks/benchmark_serving.py \
+    --model mistralai/Mistral-7B-v0.1 \
+    --tokenizer mistralai/Mistral-7B-v0.1 \
+    --endpoint /v1/completions \
+    --dataset-name sharegpt \
+    --dataset-path ShareGPT_V3_unfiltered_cleaned_split.json \
+    --request-rate 3.0
+```
+
+Navigating to [`http://localhost:8000/metrics`](http://localhost:8000/metrics) will show the raw Prometheus metrics being exposed by vLLM.
+
+### Grafana Dashboard
+
+Navigate to [`http://localhost:3000`](http://localhost:3000). Log in with the default username (`admin`) and password (`admin`).
+
+#### Add Prometheus Data Source
+
+Navigate to [`http://localhost:3000/connections/datasources/new`](http://localhost:3000/connections/datasources/new) and select Prometheus. 
+
+On Prometheus configuration page, we need to add the `Prometheus Server URL` in `Connection`. For this setup, Grafana and Prometheus are running in separate containers, but Docker creates DNS name for each containers. You can just use `http://prometheus:9090`.
+
+Click `Save & Test`. You should get a green check saying "Successfully queried the Prometheus API.".
+
+#### Import Dashboard 
+
+Navigate to [`http://localhost:3000/dashboard/import`](http://localhost:3000/dashboard/import), upload `grafana.json`, and select the `prometheus` datasource. You should see a screen that looks like the following:
+
+![Grafana Dashboard Image](https://i.imgur.com/R2vH9VW.png)

examples/production_monitoring/docker-compose.yaml

+# docker-compose.yaml
+version: "3"
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    extra_hosts:
+      - "host.docker.internal:host-gateway"     # allow a direct connection from container to the local machine
+    ports:
+      - "9090:9090"   # the default port used by Prometheus
+    volumes:
+      - ${PWD}/prometheus.yaml:/etc/prometheus/prometheus.yml # mount Prometheus config file
+
+  grafana:
+    image: grafana/grafana:latest
+    depends_on:
+      - prometheus
+    ports:
+      - "3000:3000" # the default port used by Grafana

examples/production_monitoring/grafana.json

+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS",
+      "label": "prometheus",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    }
+  ],
+  "__elements": {},
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "10.4.2"
+    },
+    {
+      "type": "panel",
+      "id": "heatmap",
+      "name": "Heatmap",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    },
+    {
+      "type": "panel",
+      "id": "timeseries",
+      "name": "Time series",
+      "version": ""
+    }
+  ],
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "target": {
+          "limit": 100,
+          "matchAny": false,
+          "tags": [],
+          "type": "dashboard"
+        },
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Monitoring vLLM Inference Server",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "End to end request latency measured in seconds.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 9,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P99",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P95",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P90",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P50",
+          "range": true,
+          "refId": "D",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "rate(vllm:e2e_request_latency_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:e2e_request_latency_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
+          "hide": false,
+          "instant": false,
+          "legendFormat": "Average",
+          "range": true,
+          "refId": "E"
+        }
+      ],
+      "title": "E2E Request Latency",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Number of tokens processed per second",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 8,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "rate(vllm:prompt_tokens_total{model_name=\"$model_name\"}[$__rate_interval])",
+          "fullMetaSearch": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "Prompt Tokens/Sec",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "rate(vllm:generation_tokens_total{model_name=\"$model_name\"}[$__rate_interval])",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "Generation Tokens/Sec",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        }
+      ],
+      "title": "Token Throughput",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Inter token latency in seconds.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 10,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P99",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P95",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P90",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P50",
+          "range": true,
+          "refId": "D",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "rate(vllm:time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
+          "hide": false,
+          "instant": false,
+          "legendFormat": "Mean",
+          "range": true,
+          "refId": "E"
+        }
+      ],
+      "title": "Time Per Output Token Latency",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Number of requests in RUNNING, WAITING, and SWAPPED state",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "vllm:num_requests_running{model_name=\"$model_name\"}",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Num Running",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "vllm:num_requests_swapped{model_name=\"$model_name\"}",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Num Swapped",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "vllm:num_requests_waiting{model_name=\"$model_name\"}",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Num Waiting",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        }
+      ],
+      "title": "Scheduler State",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "P50, P90, P95, and P99 TTFT latency in seconds.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P99",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P95",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P90",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "P50",
+          "range": true,
+          "refId": "D",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "rate(vllm:time_to_first_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:time_to_first_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
+          "hide": false,
+          "instant": false,
+          "legendFormat": "Average",
+          "range": true,
+          "refId": "E"
+        }
+      ],
+      "title": "Time To First Token Latency",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Percentage of used cache blocks by vLLM.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "vllm:gpu_cache_usage_perc{model_name=\"$model_name\"}",
+          "instant": false,
+          "legendFormat": "GPU Cache Usage",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "vllm:cpu_cache_usage_perc{model_name=\"$model_name\"}",
+          "hide": false,
+          "instant": false,
+          "legendFormat": "CPU Cache Usage",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Cache Utilization",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Heatmap of request prompt length",
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "scaleDistribution": {
+              "type": "linear"
+            }
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "id": 12,
+      "options": {
+        "calculate": false,
+        "cellGap": 1,
+        "cellValues": {
+          "unit": "none"
+        },
+        "color": {
+          "exponent": 0.5,
+          "fill": "dark-orange",
+          "min": 0,
+          "mode": "scheme",
+          "reverse": false,
+          "scale": "exponential",
+          "scheme": "Spectral",
+          "steps": 64
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
+        },
+        "filterValues": {
+          "le": 1e-9
+        },
+        "legend": {
+          "show": true
+        },
+        "rowsFrame": {
+          "layout": "auto",
+          "value": "Request count"
+        },
+        "tooltip": {
+          "mode": "single",
+          "showColorScale": false,
+          "yHistogram": true
+        },
+        "yAxis": {
+          "axisLabel": "Prompt Length",
+          "axisPlacement": "left",
+          "reverse": false,
+          "unit": "none"
+        }
+      },
+      "pluginVersion": "10.4.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "sum by(le) (increase(vllm:request_prompt_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
+          "format": "heatmap",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Request Prompt Length",
+      "type": "heatmap"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Heatmap of request generation length",
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "scaleDistribution": {
+              "type": "linear"
+            }
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "id": 13,
+      "options": {
+        "calculate": false,
+        "cellGap": 1,
+        "cellValues": {
+          "unit": "none"
+        },
+        "color": {
+          "exponent": 0.5,
+          "fill": "dark-orange",
+          "min": 0,
+          "mode": "scheme",
+          "reverse": false,
+          "scale": "exponential",
+          "scheme": "Spectral",
+          "steps": 64
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
+        },
+        "filterValues": {
+          "le": 1e-9
+        },
+        "legend": {
+          "show": true
+        },
+        "rowsFrame": {
+          "layout": "auto",
+          "value": "Request count"
+        },
+        "tooltip": {
+          "mode": "single",
+          "showColorScale": false,
+          "yHistogram": true
+        },
+        "yAxis": {
+          "axisLabel": "Generation Length",
+          "axisPlacement": "left",
+          "reverse": false,
+          "unit": "none"
+        }
+      },
+      "pluginVersion": "10.4.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "sum by(le) (increase(vllm:request_generation_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
+          "format": "heatmap",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Request Generation Length",
+      "type": "heatmap"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Number of finished requests by their finish reason: either an EOS token was generated or the max sequence length was reached.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "id": 11,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "sum by(finished_reason) (increase(vllm:request_success_total{model_name=\"$model_name\"}[$__rate_interval]))",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "interval": "",
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Finish Reason",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "",
+  "schemaVersion": 39,
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "current": {},
+        "datasource": {
+          "type": "prometheus",
+          "uid": "${DS_PROMETHEUS}"
+        },
+        "definition": "label_values(model_name)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "model_name",
+        "multi": false,
+        "name": "model_name",
+        "options": [],
+        "query": {
+          "query": "label_values(model_name)",
+          "refId": "StandardVariableQuery"
+        },
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-5m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "vLLM",
+  "uid": "b281712d-8bff-41ef-9f3f-71ad43c05e9b",
+  "version": 1,
+  "weekStart": ""
+}

examples/production_monitoring/prometheus.yaml

+# prometheus.yaml
+global:
+  scrape_interval: 5s
+  evaluation_interval: 30s
+
+scrape_configs:
+  - job_name: vllm
+    static_configs:
+      - targets:
+          - 'host.docker.internal:8000'

examples/save_sharded_state.py

+"""
+Saves each worker's model state dict directly to a checkpoint, which enables a
+fast load path for large tensor-parallel models where each worker only needs to
+read its own shard rather than the entire checkpoint.
+
+Example usage:
+
+python save_sharded_state.py \
+    --model /path/to/load \
+    --quantization deepspeedfp \
+    --tensor-parallel-size 8 \
+    --output /path/to/save
+
+Then, the model can be loaded with
+
+llm = LLM(
+    model="/path/to/save",
+    load_format="sharded_state",
+    quantization="deepspeedfp",
+    tensor_parallel_size=8,
+)
+"""
+import argparse
+import dataclasses
+import os
+import shutil
+from pathlib import Path
+
+from vllm import LLM, EngineArgs
+
+parser = argparse.ArgumentParser()
+EngineArgs.add_cli_args(parser)
+parser.add_argument("--output",
+                    "-o",
+                    required=True,
+                    type=str,
+                    help="path to output checkpoint")
+parser.add_argument("--file-pattern",
+                    type=str,
+                    help="string pattern of saved filenames")
+parser.add_argument("--max-file-size",
+                    type=str,
+                    default=5 * 1024**3,
+                    help="max size (in bytes) of each safetensors file")
+
+
+def main(args):
+    engine_args = EngineArgs.from_cli_args(args)
+    if engine_args.enable_lora:
+        raise ValueError("Saving with enable_lora=True is not supported!")
+    model_path = engine_args.model
+    if not Path(model_path).is_dir():
+        raise ValueError("model path must be a local directory")
+    # Create LLM instance from arguments
+    llm = LLM(**dataclasses.asdict(engine_args))
+    # Prepare output directory
+    Path(args.output).mkdir(exist_ok=True)
+    # Dump worker states to output directory
+    model_executor = llm.llm_engine.model_executor
+    model_executor.save_sharded_state(path=args.output,
+                                      pattern=args.file_pattern,
+                                      max_size=args.max_file_size)
+    # Copy metadata files to output directory
+    for file in os.listdir(model_path):
+        if os.path.splitext(file)[1] not in (".bin", ".pt", ".safetensors"):
+            if os.path.isdir(os.path.join(model_path, file)):
+                shutil.copytree(os.path.join(model_path, file),
+                                os.path.join(args.output, file))
+            else:
+                shutil.copy(os.path.join(model_path, file), args.output)
+
+
+if __name__ == "__main__":
+    args = parser.parse_args()
+    main(args)

examples/template_alpaca.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' %}
+### Instruction:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% elif message['role'] == 'assistant' %}
+### Response:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% elif message['role'] == 'user_context' %}
+### Input:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}
+### Response:
+{% endif %}
\ No newline at end of file

examples/template_baichuan.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' -%}
+        {{- '<reserved_106>' + message['content'] -}}
+    {%- elif message['role'] == 'assistant' -%}
+        {{- '<reserved_107>' + message['content'] -}}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
+    {{- '<reserved_107>' -}}
+{% endif %}
\ No newline at end of file

examples/template_chatglm.jinja

+{%- set counter = namespace(index=0) -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- '[Round ' + counter.index|string + ']\n问：' + message['content'] -}}
+        {%- set counter.index = counter.index + 1 -%}
+    {%- endif -%}
+    {%- if message['role'] == 'assistant' -%}
+        {{- '\n答：' + message['content'] -}}
+        {%- if (loop.last and add_generation_prompt) or not loop.last -%}
+            {{- '\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+
+{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
+    {{- '\n答：' -}}
+{%- endif -%}
\ No newline at end of file

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