Automatic Prefix Caching (APC in short) caches the KV cache of existing queries, so that a new query can directly reuse the KV cache if it shares the same prefix with one of the existing queries, allowing the new query to skip the computation of the shared part.
```{note}
Technical details on how vLLM implements APC are in the next page.
```
## Enabling APC in vLLM
Set `enable_prefix_caching=True` in vLLM engine to enable APC. Here is an example:
```python
importtime
fromvllmimportLLM,SamplingParams
# A prompt containing a large markdown table. The table is randomly generated by GPT-4.
LONG_PROMPT="You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as follows.\n# Table\n"+"""
| ID | Name | Age | Occupation | Country | Email | Phone Number | Address |
LONG_PROMPT+"Question: what is the age of John Doe? Your answer: The age of John Doe is ",
)
# Querying the age of Zack Blue
# This query will be faster since vllm avoids computing the KV cache of LONG_PROMPT again.
get_generation_time(
llm,
sampling_params,
LONG_PROMPT+"Question: what is the age of Zack Blue? Your answer: The age of Zack Blue is ",
)
```
## Example workloads
We describe two example workloads, where APC can provide huge performance benefit:
- Long document query, where the user repeatedly queries the same long document (e.g. software manual or annual report) with different queries. In this case, instead of processing the long document again and again, APC allows vLLM to process this long document *only once*, and all future requests can avoid recomputing this long document by reusing its KV cache. This allows vLLM to serve future requests with much higher throughput and much lower latency.
- Multi-round conversation, where the user may chat with the application multiple times in the same chatting session. In this case, instead of processing the whole chatting history again and again, APC allows vLLM to reuse the processing results of the chat history across all future rounds of conversation, allowing vLLM to serve future requests with much higher throughput and much lower latency.
## Limits
APC in general does not reduce the performance of vLLM. With that being said, APC only reduces the time of processing the queries (the prefilling phase) and does not reduce the time of generating new tokens (the decoding phase). So APC does not bring performance gain when vLLM spends most of the time generating answers to the queries (e.g. when the length of the answer is long), or new queries do not share the same prefix with any of existing queries (so that the computation cannot be reused).
Automatic Prefix Caching (APC in short) caches the KV cache of existing queries, so that a new query can directly reuse the KV cache if it shares the same prefix with one of the existing queries, allowing the new query to skip the computation of the shared part.
.. note::
Technical details on how vLLM implements APC are in the next page.
Enabling APC in vLLM
--------------------
Set ``enable_prefix_caching=True`` in vLLM engine to enable APC. Here is an example:
.. code-block:: python
import time
from vllm import LLM, SamplingParams
# A prompt containing a large markdown table. The table is randomly generated by GPT-4.
LONG_PROMPT = "You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as follows.\n# Table\n" + """
| ID | Name | Age | Occupation | Country | Email | Phone Number | Address |
LONG_PROMPT + "Question: what is the age of John Doe? Your answer: The age of John Doe is ",
)
# Querying the age of Zack Blue
# This query will be faster since vllm avoids computing the KV cache of LONG_PROMPT again.
get_generation_time(
llm,
sampling_params,
LONG_PROMPT + "Question: what is the age of Zack Blue? Your answer: The age of Zack Blue is ",
)
Example workloads
-----------------
We describe two example workloads, where APC can provide huge performance benefit:
- Long document query, where the user repeatedly queries the same long document (e.g. software manual or annual report) with different queries. In this case, instead of processing the long document again and again, APC allows vLLM to process this long document *only once*, and all future requests can avoid recomputing this long document by reusing its KV cache. This allows vLLM to serve future requests with much higher throughput and much lower latency.
- Multi-round conversation, where the user may chat with the application multiple times in the same chatting session. In this case, instead of processing the whole chatting history again and again, APC allows vLLM to reuse the processing results of the chat history across all future rounds of conversation, allowing vLLM to serve future requests with much higher throughput and much lower latency.
Limits
------
APC in general does not reduce the performance of vLLM. With that being said, APC only reduces the time of processing the queries (the prefilling phase) and does not reduce the time of generating new tokens (the decoding phase). So APC does not bring performance gain when vLLM spends most of the time generating answers to the queries (e.g. when the length of the answer is long), or new queries do not share the same prefix with any of existing queries (so that the computation cannot be reused).
We host regular meetups in San Francisco Bay Area every 2 months. We will share the project updates from the vLLM team and have guest speakers from the industry to share their experience and insights. Please find the materials of our previous meetups below:
-[The seventh vLLM meetup](https://lu.ma/h0qvrajz), with Snowflake, November 14th 2024. [[Slides]](https://docs.google.com/presentation/d/1e3CxQBV3JsfGp30SwyvS3eM_tW-ghOhJ9PAJGK6KR54/edit?usp=sharing)
-[The sixth vLLM meetup](https://lu.ma/87q3nvnh), with NVIDIA, September 9th 2024. [[Slides]](https://docs.google.com/presentation/d/1wrLGwytQfaOTd5wCGSPNhoaW3nq0E-9wqyP7ny93xRs/edit?usp=sharing)
-[The fifth vLLM meetup](https://lu.ma/lp0gyjqr), with AWS, July 24th 2024. [[Slides]](https://docs.google.com/presentation/d/1RgUD8aCfcHocghoP3zmXzck9vX3RCI9yfUAB2Bbcl4Y/edit?usp=sharing)
-[The fourth vLLM meetup](https://lu.ma/agivllm), with Cloudflare and BentoML, June 11th 2024. [[Slides]](https://docs.google.com/presentation/d/1iJ8o7V2bQEi0BFEljLTwc5G1S10_Rhv3beed5oB0NJ4/edit?usp=sharing)
-[The third vLLM meetup](https://robloxandvllmmeetup2024.splashthat.com/), with Roblox, April 2nd 2024. [[Slides]](https://docs.google.com/presentation/d/1A--47JAK4BJ39t954HyTkvtfwn0fkqtsL8NGFuslReM/edit?usp=sharing)
-[The second vLLM meetup](https://lu.ma/ygxbpzhl), with IBM Research, January 31st 2024. [[Slides]](https://docs.google.com/presentation/d/12mI2sKABnUw5RBWXDYY-HtHth4iMSNcEoQ10jDQbxgA/edit?usp=sharing)[[Video (vLLM Update)]](https://youtu.be/Y0C-DUvEnZQ) [[Video (IBM Research & torch.compile)]](https://youtu.be/m0dMtFLI-dg)
-[The first vLLM meetup](https://lu.ma/first-vllm-meetup), with a16z, October 5th 2023. [[Slides]](https://docs.google.com/presentation/d/1QL-XPFXiFpDBh86DbEegFXBXFXjix4v032GhShbKf3s/edit?usp=sharing)
We are always looking for speakers and sponsors at San Francisco Bay Area and potentially other locations. If you are interested in speaking or sponsoring, please contact us at [vllm-questions@lists.berkeley.edu](mailto:vllm-questions@lists.berkeley.edu).
We host regular meetups in San Francisco Bay Area every 2 months. We will share the project updates from the vLLM team and have guest speakers from the industry to share their experience and insights. Please find the materials of our previous meetups below:
- `The seventh vLLM meetup <https://lu.ma/h0qvrajz>`__, with Snowflake, November 14th 2024. `[Slides] <https://docs.google.com/presentation/d/1e3CxQBV3JsfGp30SwyvS3eM_tW-ghOhJ9PAJGK6KR54/edit?usp=sharing>`__
- `The sixth vLLM meetup <https://lu.ma/87q3nvnh>`__, with NVIDIA, September 9th 2024. `[Slides] <https://docs.google.com/presentation/d/1wrLGwytQfaOTd5wCGSPNhoaW3nq0E-9wqyP7ny93xRs/edit?usp=sharing>`__
- `The fifth vLLM meetup <https://lu.ma/lp0gyjqr>`__, with AWS, July 24th 2024. `[Slides] <https://docs.google.com/presentation/d/1RgUD8aCfcHocghoP3zmXzck9vX3RCI9yfUAB2Bbcl4Y/edit?usp=sharing>`__
- `The fourth vLLM meetup <https://lu.ma/agivllm>`__, with Cloudflare and BentoML, June 11th 2024. `[Slides] <https://docs.google.com/presentation/d/1iJ8o7V2bQEi0BFEljLTwc5G1S10_Rhv3beed5oB0NJ4/edit?usp=sharing>`__
- `The third vLLM meetup <https://robloxandvllmmeetup2024.splashthat.com/>`__, with Roblox, April 2nd 2024. `[Slides] <https://docs.google.com/presentation/d/1A--47JAK4BJ39t954HyTkvtfwn0fkqtsL8NGFuslReM/edit?usp=sharing>`__
- `The second vLLM meetup <https://lu.ma/ygxbpzhl>`__, with IBM Research, January 31st 2024. `[Slides] <https://docs.google.com/presentation/d/12mI2sKABnUw5RBWXDYY-HtHth4iMSNcEoQ10jDQbxgA/edit?usp=sharing>`__ `[Video (vLLM Update)] <https://youtu.be/Y0C-DUvEnZQ>`__ `[Video (IBM Research & torch.compile)] <https://youtu.be/m0dMtFLI-dg>`__
- `The first vLLM meetup <https://lu.ma/first-vllm-meetup>`__, with a16z, October 5th 2023. `[Slides] <https://docs.google.com/presentation/d/1QL-XPFXiFpDBh86DbEegFXBXFXjix4v032GhShbKf3s/edit?usp=sharing>`__
We are always looking for speakers and sponsors at San Francisco Bay Area and potentially other locations. If you are interested in speaking or sponsoring, please contact us at `vllm-questions@lists.berkeley.edu <mailto:vllm-questions@lists.berkeley.edu>`__.
See `here <https://github.com/vllm-project/vllm/blob/main/Dockerfile>`__ for the main Dockerfile to construct
the image for running an OpenAI compatible server with vLLM. More information about deploying with Docker can be found `here <https://docs.vllm.ai/en/stable/serving/deploying_with_docker.html>`__.
Below is a visual representation of the multi-stage Dockerfile. The build graph contains the following nodes:
- All build stages
- The default build target (highlighted in grey)
- External images (with dashed borders)
The edges of the build graph represent:
- FROM ... dependencies (with a solid line and a full arrow head)
- COPY --from=... dependencies (with a dashed line and an empty arrow head)
- RUN --mount=(.*)from=... dependencies (with a dotted line and an empty diamond arrow head)
Thank you for your interest in contributing to vLLM! Our community is open to everyone and welcomes all kinds of contributions, no matter how small or large. There are several ways you can contribute to the project:
Thank you for your interest in contributing to vLLM! Our community is open to everyone and welcomes all kinds of contributions, no matter how small or large. There are several ways you can contribute to the project:
...
@@ -12,132 +11,121 @@ We also believe in the power of community support; thus, answering queries, offe
...
@@ -12,132 +11,121 @@ We also believe in the power of community support; thus, answering queries, offe
Finally, one of the most impactful ways to support us is by raising awareness about vLLM. Talk about it in your blog posts and highlight how it's driving your incredible projects. Express your support on social media if you're using vLLM, or simply offer your appreciation by starring our repository!
Finally, one of the most impactful ways to support us is by raising awareness about vLLM. Talk about it in your blog posts and highlight how it's driving your incredible projects. Express your support on social media if you're using vLLM, or simply offer your appreciation by starring our repository!
License
## License
-------
See `LICENSE <https://github.com/vllm-project/vllm/tree/main/LICENSE>`_.
See <gh-file:LICENSE>.
Developing
## Developing
----------
Depending on the kind of development you'd like to do (e.g. Python, CUDA), you can choose to build vLLM with or without compilation. Check out the `building from source <https://docs.vllm.ai/en/latest/getting_started/installation.html#build-from-source>`_ documentation for details.
Depending on the kind of development you'd like to do (e.g. Python, CUDA), you can choose to build vLLM with or without compilation.
Check out the [building from source](#build-from-source) documentation for details.
Testing
## Testing
-------
.. code-block:: bash
```bash
pip install-r requirements-dev.txt
pip install -r requirements-dev.txt
# linting and formatting
bash format.sh
# Static type checking
mypy
# Unit tests
pytest tests/
```
# linting and formatting
```{note}
bash format.sh
Currently, the repository does not pass the `mypy` tests.
# Static type checking
```
mypy
# Unit tests
pytest tests/
.. note:: Currently, the repository does not pass the ``mypy`` tests.
# Contribution Guidelines
Contribution Guidelines
## Issues
=======================
Issues
If you encounter a bug or have a feature request, please [search existing issues](https://github.com/vllm-project/vllm/issues?q=is%3Aissue) first to see if it has already been reported. If not, please [file a new issue](https://github.com/vllm-project/vllm/issues/new/choose), providing as much relevant information as possible.
------
If you encounter a bug or have a feature request, please `search existing issues <https://github.com/vllm-project/vllm/issues?q=is%3Aissue>`_ first to see if it has already been reported. If not, please `file a new issue <https://github.com/vllm-project/vllm/issues/new/choose>`_, providing as much relevant information as possible.
```{important}
If you discover a security vulnerability, please follow the instructions [here](gh-file:SECURITY.md#reporting-a-vulnerability).
```
.. important::
## Pull Requests & Code Reviews
If you discover a security vulnerability, please follow the instructions `here <https://github.com/vllm-project/vllm/tree/main/SECURITY.md#reporting-a-vulnerability>`_.
Pull Requests & Code Reviews
----------------------------
Thank you for your contribution to vLLM! Before submitting the pull request,
Thank you for your contribution to vLLM! Before submitting the pull request,
please ensure the PR meets the following criteria. This helps vLLM maintain the
please ensure the PR meets the following criteria. This helps vLLM maintain the
code quality and improve the efficiency of the review process.
code quality and improve the efficiency of the review process.
DCO and Signed-off-by
### DCO and Signed-off-by
^^^^^^^^^^^^^^^^^^^^^
When contributing changes to this project, you must agree to the `DCO <https://github.com/vllm-project/vllm/tree/main/DCO>`_.
When contributing changes to this project, you must agree to the <gh-file:DCO>.
Commits must include a ``Signed-off-by:`` header which certifies agreement with
Commits must include a `Signed-off-by:` header which certifies agreement with
the terms of the `DCO <https://github.com/vllm-project/vllm/tree/main/DCO>`_.
the terms of the DCO.
Using ``-s`` with ``git commit`` will automatically add this header.
Using `-s` with `git commit` will automatically add this header.
PR Title and Classification
### PR Title and Classification
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Only specific types of PRs will be reviewed. The PR title is prefixed
Only specific types of PRs will be reviewed. The PR title is prefixed
appropriately to indicate the type of change. Please use one of the following:
appropriately to indicate the type of change. Please use one of the following:
- ``[Bugfix]`` for bug fixes.
-`[Bugfix]` for bug fixes.
- ``[CI/Build]`` for build or continuous integration improvements.
-`[CI/Build]` for build or continuous integration improvements.
- ``[Doc]`` for documentation fixes and improvements.
-`[Doc]` for documentation fixes and improvements.
- ``[Model]`` for adding a new model or improving an existing model. Model name
-`[Model]` for adding a new model or improving an existing model. Model name
should appear in the title.
should appear in the title.
- ``[Frontend]`` For changes on the vLLM frontend (e.g., OpenAI API server,
-`[Frontend]` For changes on the vLLM frontend (e.g., OpenAI API server,
``LLM`` class, etc.)
`LLM` class, etc.)
- ``[Kernel]`` for changes affecting CUDA kernels or other compute kernels.
-`[Kernel]` for changes affecting CUDA kernels or other compute kernels.
- ``[Core]`` for changes in the core vLLM logic (e.g., ``LLMEngine``,
-`[Core]` for changes in the core vLLM logic (e.g., `LLMEngine`,
``AsyncLLMEngine``, ``Scheduler``, etc.)
`AsyncLLMEngine`, `Scheduler`, etc.)
- ``[Hardware][Vendor]`` for hardware-specific changes. Vendor name should
-`[Hardware][Vendor]` for hardware-specific changes. Vendor name should
appear in the prefix (e.g., ``[Hardware][AMD]``).
appear in the prefix (e.g., `[Hardware][AMD]`).
- ``[Misc]`` for PRs that do not fit the above categories. Please use this
-`[Misc]` for PRs that do not fit the above categories. Please use this
sparingly.
sparingly.
.. note::
```{note}
If the PR spans more than one category, please include all relevant prefixes.
If the PR spans more than one category, please include all relevant prefixes.
```
Code Quality
### Code Quality
^^^^^^^^^^^^
The PR needs to meet the following code quality standards:
The PR needs to meet the following code quality standards:
- We adhere to `Google Python style guide
- We adhere to [Google Python style guide](https://google.github.io/styleguide/pyguide.html) and [Google C++ style guide](https://google.github.io/styleguide/cppguide.html).
<https://google.github.io/styleguide/pyguide.html>`_ and `Google C++ style guide
- Pass all linter checks. Please use <gh-file:format.sh> to format your code.
We support tracing vLLM workers using the `torch.profiler` module. You can enable tracing by setting the `VLLM_TORCH_PROFILER_DIR` environment variable to the directory where you want to save the traces: `VLLM_TORCH_PROFILER_DIR=/mnt/traces/`
The OpenAI server also needs to be started with the `VLLM_TORCH_PROFILER_DIR` environment variable set.
When using `benchmarks/benchmark_serving.py`, you can enable profiling by passing the `--profile` flag.
```{warning}
Only enable profiling in a development environment.
```
Traces can be visualized using <https://ui.perfetto.dev/>.
```{tip}
Only send a few requests through vLLM when profiling, as the traces can get quite large. Also, no need to untar the traces, they can be viewed directly.
```
```{tip}
To stop the profiler - it flushes out all the profile trace files to the directory. This takes time, for example for about 100 requests worth of data for a llama 70b, it takes about 10 minutes to flush out on a H100.
Set the env variable VLLM_RPC_TIMEOUT to a big number before you start the server. Say something like 30 minutes.
`export VLLM_RPC_TIMEOUT=1800000`
```
## Example commands and usage
### Offline Inference
Refer to <gh-file:examples/offline_inference_with_profiler.py> for an example.
We support tracing vLLM workers using the ``torch.profiler`` module. You can enable tracing by setting the ``VLLM_TORCH_PROFILER_DIR`` environment variable to the directory where you want to save the traces: ``VLLM_TORCH_PROFILER_DIR=/mnt/traces/``
The OpenAI server also needs to be started with the ``VLLM_TORCH_PROFILER_DIR`` environment variable set.
When using ``benchmarks/benchmark_serving.py``, you can enable profiling by passing the ``--profile`` flag.
.. warning::
Only enable profiling in a development environment.
Traces can be visualized using https://ui.perfetto.dev/.
.. tip::
Only send a few requests through vLLM when profiling, as the traces can get quite large. Also, no need to untar the traces, they can be viewed directly.
.. tip::
To stop the profiler - it flushes out all the profile trace files to the directory. This takes time, for example for about 100 requests worth of data for a llama 70b, it takes about 10 minutes to flush out on a H100.
Set the env variable VLLM_RPC_TIMEOUT to a big number before you start the server. Say something like 30 minutes.
``export VLLM_RPC_TIMEOUT=1800000``
Example commands and usage:
===========================
Offline Inference:
------------------
Refer to `examples/offline_inference_with_profiler.py <https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_with_profiler.py>`_ for an example.
containing all the necessary information. The [VllmConfig](https://github.com/vllm-project/vllm/blob/d1c6799b8870e513bf4f2305cbf6cda9fc3d773b/vllm/config.py#L2036)
To avoid accidentally passing incorrect arguments, the constructor is now keyword-only. This ensures that the constructor will raise an error if old configurations are passed. vLLM developers have already made this change for all models within vLLM. For out-of-tree registered models, developers need to update their models, for example by adding shim code to adapt the old constructor signature to the new one:
This document describes how vLLM integrates with HuggingFace libraries. We will explain step by step what happens under the hood when we run `vllm serve`.
Let's say we want to serve the popular QWen model by running `vllm serve Qwen/Qwen2-7B`.
1. The `model` argument is `Qwen/Qwen2-7B`. vLLM determines whether this model exists by checking for the corresponding config file `config.json`. See this [code snippet](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L162-L182) for the implementation. Within this process:
- If the `model` argument corresponds to an existing local path, vLLM will load the config file directly from this path.
- If the `model` argument is a HuggingFace model ID consisting of a username and model name, vLLM will first try to use the config file from the HuggingFace local cache, using the `model` argument as the model name and the `--revision` argument as the revision. See [their website](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables#hfhome) for more information on how the HuggingFace cache works.
- If the `model` argument is a HuggingFace model ID but it is not found in the cache, vLLM will download the config file from the HuggingFace model hub. Refer to [this function](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L91) for the implementation. The input arguments include the `model` argument as the model name, the `--revision` argument as the revision, and the environment variable `HF_TOKEN` as the token to access the model hub. In our case, vLLM will download the [config.json](https://huggingface.co/Qwen/Qwen2-7B/blob/main/config.json) file.
2. After confirming the existence of the model, vLLM loads its config file and converts it into a dictionary. See this [code snippet](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L185-L186) for the implementation.
3. Next, vLLM [inspects](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L189) the `model_type` field in the config dictionary to [generate](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#190-L216) the config object to use. There are some `model_type` values that vLLM directly supports; see [here](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L48) for the list. If the `model_type` is not in the list, vLLM will use [AutoConfig.from_pretrained](https://huggingface.co/docs/transformers/en/model_doc/auto#transformers.AutoConfig.from_pretrained) to load the config class, with `model`, `--revision`, and `--trust_remote_code` as the arguments. Please note that:
- HuggingFace also has its own logic to determine the config class to use. It will again use the `model_type` field to search for the class name in the transformers library; see [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models) for the list of supported models. If the `model_type` is not found, HuggingFace will use the `auto_map` field from the config JSON file to determine the class name. Specifically, it is the `AutoConfig` field under `auto_map`. See [DeepSeek](https://huggingface.co/deepseek-ai/DeepSeek-V2.5/blob/main/config.json) for an example.
- The `AutoConfig` field under `auto_map` points to a module path in the model's repository. To create the config class, HuggingFace will import the module and use the `from_pretrained` method to load the config class. This can generally cause arbitrary code execution, so it is only executed when `--trust_remote_code` is enabled.
4. Subsequently, vLLM applies some historical patches to the config object. These are mostly related to RoPE configuration; see [here](https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/config.py#L244) for the implementation.
5. Finally, vLLM can reach the model class we want to initialize. vLLM uses the `architectures` field in the config object to determine the model class to initialize, as it maintains the mapping from architecture name to model class in [its registry](https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/model_executor/models/registry.py#L80). If the architecture name is not found in the registry, it means this model architecture is not supported by vLLM. For `Qwen/Qwen2-7B`, the `architectures` field is `["Qwen2ForCausalLM"]`, which corresponds to the `Qwen2ForCausalLM` class in [vLLM's code](https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/model_executor/models/qwen2.py#L364). This class will initialize itself depending on various configs.
Beyond that, there are two more things vLLM depends on HuggingFace for.
1.**Tokenizer**: vLLM uses the tokenizer from HuggingFace to tokenize the input text. The tokenizer is loaded using [AutoTokenizer.from_pretrained](https://huggingface.co/docs/transformers/en/model_doc/auto#transformers.AutoTokenizer.from_pretrained) with the `model` argument as the model name and the `--revision` argument as the revision. It is also possible to use a tokenizer from another model by specifying the `--tokenizer` argument in the `vllm serve` command. Other relevant arguments are `--tokenizer-revision` and `--tokenizer-mode`. Please check HuggingFace's documentation for the meaning of these arguments. This part of the logic can be found in the [get_tokenizer](https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/tokenizer.py#L87) function. After obtaining the tokenizer, notably, vLLM will cache some expensive attributes of the tokenizer in [get_cached_tokenizer](https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/tokenizer.py#L24).
2.**Model weight**: vLLM downloads the model weight from the HuggingFace model hub using the `model` argument as the model name and the `--revision` argument as the revision. vLLM provides the argument `--load-format` to control what files to download from the model hub. By default, it will try to load the weights in the safetensors format and fall back to the PyTorch bin format if the safetensors format is not available. We can also pass `--load-format dummy` to skip downloading the weights.
- It is recommended to use the safetensors format, as it is efficient for loading in distributed inference and also safe from arbitrary code execution. See the [documentation](https://huggingface.co/docs/safetensors/en/index) for more information on the safetensors format. This part of the logic can be found [here](https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/model_executor/model_loader/loader.py#L385). Please note that:
This completes the integration between vLLM and HuggingFace.
In summary, vLLM reads the config file `config.json`, tokenizer, and model weight from the HuggingFace model hub or a local directory. It uses the config class from either vLLM, HuggingFace transformers, or loads the config class from the model's repository.
This document describes how vLLM integrates with HuggingFace libraries. We will explain step by step what happens under the hood when we run ``vllm serve``.
Let's say we want to serve the popular QWen model by running ``vllm serve Qwen/Qwen2-7B``.
1. The ``model`` argument is ``Qwen/Qwen2-7B``. vLLM determines whether this model exists by checking for the corresponding config file ``config.json``. See this `code snippet <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L162-L182>`__ for the implementation. Within this process:
- If the ``model`` argument corresponds to an existing local path, vLLM will load the config file directly from this path.
- If the ``model`` argument is a HuggingFace model ID consisting of a username and model name, vLLM will first try to use the config file from the HuggingFace local cache, using the ``model`` argument as the model name and the ``--revision`` argument as the revision. See `their website <https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables#hfhome>`__ for more information on how the HuggingFace cache works.
- If the ``model`` argument is a HuggingFace model ID but it is not found in the cache, vLLM will download the config file from the HuggingFace model hub. Refer to `this function <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L91>`__ for the implementation. The input arguments include the ``model`` argument as the model name, the ``--revision`` argument as the revision, and the environment variable ``HF_TOKEN`` as the token to access the model hub. In our case, vLLM will download the `config.json <https://huggingface.co/Qwen/Qwen2-7B/blob/main/config.json>`__ file.
2. After confirming the existence of the model, vLLM loads its config file and converts it into a dictionary. See this `code snippet <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L185-L186>`__ for the implementation.
3. Next, vLLM `inspects <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L189>`__ the ``model_type`` field in the config dictionary to `generate <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#190-L216>`__ the config object to use. There are some ``model_type`` values that vLLM directly supports; see `here <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/transformers_utils/config.py#L48>`__ for the list. If the ``model_type`` is not in the list, vLLM will use `AutoConfig.from_pretrained <https://huggingface.co/docs/transformers/en/model_doc/auto#transformers.AutoConfig.from_pretrained>`__ to load the config class, with ``model``, ``--revision``, and ``--trust_remote_code`` as the arguments. Please note that:
- HuggingFace also has its own logic to determine the config class to use. It will again use the ``model_type`` field to search for the class name in the transformers library; see `here <https://github.com/huggingface/transformers/tree/main/src/transformers/models>`__ for the list of supported models. If the ``model_type`` is not found, HuggingFace will use the ``auto_map`` field from the config JSON file to determine the class name. Specifically, it is the ``AutoConfig`` field under ``auto_map``. See `DeepSeek <https://huggingface.co/deepseek-ai/DeepSeek-V2.5/blob/main/config.json>`__ for an example.
- The ``AutoConfig`` field under ``auto_map`` points to a module path in the model's repository. To create the config class, HuggingFace will import the module and use the ``from_pretrained`` method to load the config class. This can generally cause arbitrary code execution, so it is only executed when ``--trust_remote_code`` is enabled.
4. Subsequently, vLLM applies some historical patches to the config object. These are mostly related to RoPE configuration; see `here <https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/config.py#L244>`__ for the implementation.
5. Finally, vLLM can reach the model class we want to initialize. vLLM uses the ``architectures`` field in the config object to determine the model class to initialize, as it maintains the mapping from architecture name to model class in `its registry <https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/model_executor/models/registry.py#L80>`__. If the architecture name is not found in the registry, it means this model architecture is not supported by vLLM. For ``Qwen/Qwen2-7B``, the ``architectures`` field is ``["Qwen2ForCausalLM"]``, which corresponds to the ``Qwen2ForCausalLM`` class in `vLLM's code <https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/model_executor/models/qwen2.py#L364>`__. This class will initialize itself depending on various configs.
Beyond that, there are two more things vLLM depends on HuggingFace for.
1. **Tokenizer**: vLLM uses the tokenizer from HuggingFace to tokenize the input text. The tokenizer is loaded using `AutoTokenizer.from_pretrained <https://huggingface.co/docs/transformers/en/model_doc/auto#transformers.AutoTokenizer.from_pretrained>`__ with the ``model`` argument as the model name and the ``--revision`` argument as the revision. It is also possible to use a tokenizer from another model by specifying the ``--tokenizer`` argument in the ``vllm serve`` command. Other relevant arguments are ``--tokenizer-revision`` and ``--tokenizer-mode``. Please check HuggingFace's documentation for the meaning of these arguments. This part of the logic can be found in the `get_tokenizer <https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/tokenizer.py#L87>`__ function. After obtaining the tokenizer, notably, vLLM will cache some expensive attributes of the tokenizer in `get_cached_tokenizer <https://github.com/vllm-project/vllm/blob/127c07480ecea15e4c2990820c457807ff78a057/vllm/transformers_utils/tokenizer.py#L24>`__.
2. **Model weight**: vLLM downloads the model weight from the HuggingFace model hub using the ``model`` argument as the model name and the ``--revision`` argument as the revision. vLLM provides the argument ``--load-format`` to control what files to download from the model hub. By default, it will try to load the weights in the safetensors format and fall back to the PyTorch bin format if the safetensors format is not available. We can also pass ``--load-format dummy`` to skip downloading the weights.
- It is recommended to use the safetensors format, as it is efficient for loading in distributed inference and also safe from arbitrary code execution. See the `documentation <https://huggingface.co/docs/safetensors/en/index>`__ for more information on the safetensors format. This part of the logic can be found `here <https://github.com/vllm-project/vllm/blob/10b67d865d92e376956345becafc249d4c3c0ab7/vllm/model_executor/model_loader/loader.py#L385>`__. Please note that:
This completes the integration between vLLM and HuggingFace.
In summary, vLLM reads the config file ``config.json``, tokenizer, and model weight from the HuggingFace model hub or a local directory. It uses the config class from either vLLM, HuggingFace transformers, or loads the config class from the model's repository.
1. Input data is passed to :class:`~vllm.LLMEngine` (or :class:`~vllm.AsyncLLMEngine`).
1. Input data is passed to {class}`~vllm.LLMEngine` (or {class}`~vllm.AsyncLLMEngine`).
2. Tokenize the data if necessary.
2. Tokenize the data if necessary.
3. Process the inputs using :meth:`INPUT_REGISTRY.process_input <vllm.inputs.registry.InputRegistry.process_input>`.
3. Process the inputs using {meth}`INPUT_REGISTRY.process_input <vllm.inputs.registry.InputRegistry.process_input>`.
- For example, add placeholder tokens to reserve KV cache for multi-modal embeddings.
- For example, add placeholder tokens to reserve KV cache for multi-modal embeddings.
4. Send the processed inputs to :class:`~vllm.executor.executor_base.ExecutorBase`.
4. Send the processed inputs to {class}`~vllm.executor.executor_base.ExecutorBase`.
5. Distribute the inputs via :class:`~vllm.worker.worker_base.WorkerBase` to :class:`~vllm.worker.model_runner_base.ModelRunnerBase`.
5. Distribute the inputs via {class}`~vllm.worker.worker_base.WorkerBase` to {class}`~vllm.worker.model_runner_base.ModelRunnerBase`.
6. If the data contains multi-modal data, convert it into keyword arguments using :meth:`MULTIMODAL_REGISTRY.map_input <vllm.multimodal.MultiModalRegistry.map_input>`.
6. If the data contains multi-modal data, convert it into keyword arguments using {meth}`MULTIMODAL_REGISTRY.map_input <vllm.multimodal.MultiModalRegistry.map_input>`.
- For example, convert a :class:`PIL.Image.Image` input to its pixel values for a vision model.
- For example, convert a {class}`PIL.Image.Image` input to its pixel values for a vision model.
This document teaches you how to add a new modality to vLLM.
Each modality in vLLM is represented by a {class}`~vllm.multimodal.MultiModalPlugin` and registered to {data}`~vllm.multimodal.MULTIMODAL_REGISTRY`.
For vLLM to recognize a new modality type, you have to create a new plugin and then pass it to {meth}`~vllm.multimodal.MultiModalRegistry.register_plugin`.
The remainder of this document details how to define custom {class}`~vllm.multimodal.MultiModalPlugin` s.
```{note}
This article is a work in progress.
```
% TODO: Add more instructions on how to add new plugins once embeddings is in.
This document teaches you how to add a new modality to vLLM.
Each modality in vLLM is represented by a :class:`~vllm.multimodal.MultiModalPlugin` and registered to :data:`~vllm.multimodal.MULTIMODAL_REGISTRY`.
For vLLM to recognize a new modality type, you have to create a new plugin and then pass it to :meth:`~vllm.multimodal.MultiModalRegistry.register_plugin`.
The remainder of this document details how to define custom :class:`~vllm.multimodal.MultiModalPlugin` s.
.. note::
This article is a work in progress.
..
TODO: Add more instructions on how to add new plugins once embeddings is in.
