From b7e62d3454afc807ddcc2fe3a56ce075461f1bc4 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Mon, 19 Jun 2023 20:03:40 -0700 Subject: [PATCH] Fix repo & documentation URLs (#163) --- README.md | 12 ++++++------ docs/source/conf.py | 2 +- docs/source/getting_started/installation.rst | 2 +- docs/source/getting_started/quickstart.rst | 10 +++++----- docs/source/index.rst | 6 +++--- docs/source/models/adding_model.rst | 10 +++++----- docs/source/models/supported_models.rst | 2 +- 7 files changed, 22 insertions(+), 22 deletions(-) diff --git a/README.md b/README.md index e2b439b4..e3c15707 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Easy, fast, and cheap LLM serving for everyone

-| Documentation | Blog | +| Documentation | Blog |

@@ -46,7 +46,7 @@ vLLM seamlessly supports many Huggingface models, including the following archit - LLaMA (e.g., `lmsys/vicuna-13b-v1.3`, `young-geng/koala`, `openlm-research/open_llama_13b`, etc.) - OPT (e.g., `facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc.) -Install vLLM with pip or [from source](https://llm-serving-cacheflow.readthedocs-hosted.com/en/latest/getting_started/installation.html#build-from-source): +Install vLLM with pip or [from source](https://vllm.readthedocs.io/en/latest/getting_started/installation.html#build-from-source): ```bash pip install vllm @@ -54,10 +54,10 @@ pip install vllm ## Getting Started -Visit our [documentation](https://llm-serving-cacheflow.readthedocs-hosted.com/_/sharing/Cyo52MQgyoAWRQ79XA4iA2k8euwzzmjY?next=/en/latest/) to get started. -- [Installation](https://llm-serving-cacheflow.readthedocs-hosted.com/_/sharing/Cyo52MQgyoAWRQ79XA4iA2k8euwzzmjY?next=/en/latest/getting_started/installation.html) -- [Quickstart](https://llm-serving-cacheflow.readthedocs-hosted.com/_/sharing/Cyo52MQgyoAWRQ79XA4iA2k8euwzzmjY?next=/en/latest/getting_started/quickstart.html) -- [Supported Models](https://llm-serving-cacheflow.readthedocs-hosted.com/_/sharing/Cyo52MQgyoAWRQ79XA4iA2k8euwzzmjY?next=/en/latest/models/supported_models.html) +Visit our [documentation](https://vllm.readthedocs.io/en/latest/) to get started. +- [Installation](https://vllm.readthedocs.io/en/latest/getting_started/installation.html) +- [Quickstart](https://vllm.readthedocs.io/en/latest/getting_started/quickstart.html) +- [Supported Models](https://vllm.readthedocs.io/en/latest/models/supported_models.html) ## Performance diff --git a/docs/source/conf.py b/docs/source/conf.py index 74d4acea..d0c64cf5 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -57,7 +57,7 @@ html_logo = 'assets/logos/vllm-logo-text-light.png' html_theme_options = { 'logo_only': True, 'path_to_docs': 'docs/source', - 'repository_url': 'https://github.com/WoosukKwon/vllm', + 'repository_url': 'https://github.com/vllm-project/vllm', 'use_repository_button': True, } diff --git a/docs/source/getting_started/installation.rst b/docs/source/getting_started/installation.rst index 824a7412..421bf19c 100644 --- a/docs/source/getting_started/installation.rst +++ b/docs/source/getting_started/installation.rst @@ -52,6 +52,6 @@ You can also build and install vLLM from source: .. code-block:: console - $ git clone https://github.com/WoosukKwon/vllm.git + $ git clone https://github.com/vllm-project/vllm.git $ cd vllm $ pip install -e . # This may take 5-10 minutes. diff --git a/docs/source/getting_started/quickstart.rst b/docs/source/getting_started/quickstart.rst index 7e3064ac..8b26ade0 100644 --- a/docs/source/getting_started/quickstart.rst +++ b/docs/source/getting_started/quickstart.rst @@ -22,7 +22,7 @@ Import ``LLM`` and ``SamplingParams`` from vLLM. The ``LLM`` class is the main c from vllm import LLM, SamplingParams -Define the list of input prompts and the sampling parameters for generation. The sampling temperature is set to 0.8 and the nucleus sampling probability is set to 0.95. For more information about the sampling parameters, refer to the `class definition `_. +Define the list of input prompts and the sampling parameters for generation. The sampling temperature is set to 0.8 and the nucleus sampling probability is set to 0.95. For more information about the sampling parameters, refer to the `class definition `_. .. code-block:: python @@ -53,13 +53,13 @@ Call ``llm.generate`` to generate the outputs. It adds the input prompts to vLLM print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") -The code example can also be found in `examples/offline_inference.py `_. +The code example can also be found in `examples/offline_inference.py `_. API Server ---------- -vLLM can be deployed as an LLM service. We provide an example `FastAPI `_ server. Check `vllm/entrypoints/api_server.py `_ for the server implementation. The server uses ``AsyncLLMEngine`` class to support asynchronous processing of incoming requests. +vLLM can be deployed as an LLM service. We provide an example `FastAPI `_ server. Check `vllm/entrypoints/api_server.py `_ for the server implementation. The server uses ``AsyncLLMEngine`` class to support asynchronous processing of incoming requests. Start the server: @@ -81,7 +81,7 @@ Query the model in shell: $ "temperature": 0 $ }' -See `examples/api_client.py `_ for a more detailed client example. +See `examples/api_client.py `_ for a more detailed client example. OpenAI-Compatible Server ------------------------ @@ -128,4 +128,4 @@ Since this server is compatible with OpenAI API, you can use it as a drop-in rep prompt="San Francisco is a") print("Completion result:", completion) -For a more detailed client example, refer to `examples/openai_client.py `_. +For a more detailed client example, refer to `examples/openai_client.py `_. diff --git a/docs/source/index.rst b/docs/source/index.rst index c95d0cc2..3f01b17e 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -15,9 +15,9 @@ Welcome to vLLM!

- Star - Watch - Fork + Star + Watch + Fork

diff --git a/docs/source/models/adding_model.rst b/docs/source/models/adding_model.rst index d89579e5..479eb989 100644 --- a/docs/source/models/adding_model.rst +++ b/docs/source/models/adding_model.rst @@ -11,22 +11,22 @@ This document provides a high-level guide on integrating a `HuggingFace Transfor However, for models that include new operators (e.g., a new attention mechanism), the process can be a bit more complex. .. tip:: - If you are encountering issues while integrating your model into vLLM, feel free to open an issue on our `GitHub `_ repository. + If you are encountering issues while integrating your model into vLLM, feel free to open an issue on our `GitHub `_ repository. We will be happy to help you out! 0. Fork the vLLM repository -------------------------------- -Start by forking our `GitHub `_ repository and then :ref:`build it from source `. +Start by forking our `GitHub `_ repository and then :ref:`build it from source `. This gives you the ability to modify the codebase and test your model. 1. Bring your model code ------------------------ -Clone the PyTorch model code from the HuggingFace Transformers repository and put it into the `vllm/model_executor/models `_ directory. -For instance, vLLM's `OPT model `_ was adpated from the HuggingFace's `modeling_opt.py `_ file. +Clone the PyTorch model code from the HuggingFace Transformers repository and put it into the `vllm/model_executor/models `_ directory. +For instance, vLLM's `OPT model `_ was adpated from the HuggingFace's `modeling_opt.py `_ file. .. warning:: When copying the model code, make sure to review and adhere to the code's copyright and licensing terms. @@ -91,4 +91,4 @@ While the process is straightforward for most layers, the tensor-parallel layers 5. Register your model ---------------------- -Finally, include your :code:`*ForCausalLM` class in `vllm/model_executor/models/__init__.py `_ and register it to the :code:`_MODEL_REGISTRY` in `vllm/model_executor/model_loader.py `_. +Finally, include your :code:`*ForCausalLM` class in `vllm/model_executor/models/__init__.py `_ and register it to the :code:`_MODEL_REGISTRY` in `vllm/model_executor/model_loader.py `_. diff --git a/docs/source/models/supported_models.rst b/docs/source/models/supported_models.rst index b5ce4eb6..a9dad0fe 100644 --- a/docs/source/models/supported_models.rst +++ b/docs/source/models/supported_models.rst @@ -29,7 +29,7 @@ Alongside each architecture, we include some popular models that use it. If your model uses one of the above model architectures, you can seamlessly run your model with vLLM. Otherwise, please refer to :ref:`Adding a New Model ` for instructions on how to implement support for your model. -Alternatively, you can raise an issue on our `GitHub `_ project. +Alternatively, you can raise an issue on our `GitHub `_ project. .. tip:: The easiest way to check if your model is supported is to run the program below: