Merge branch 'h2ovl-mississippi' of https://github.com/cooleel/vllm i…

…nto h2ovl-mississippi

.github/dependabot.yml

@@ -14,6 +14,15 @@ updates:
     reviewers: ["khluu", "simon-mo"]
     allow:
       - dependency-type: "all"
+    ignore:
+      - dependency-name: "torch"
+      - dependency-name: "torchvision"
+      - dependency-name: "xformers"
+      - dependency-name: "lm-format-enforcer"
+      - dependency-name: "gguf"
+      - dependency-name: "compressed-tensors"
+      - dependency-name: "ray[adag]"
+      - dependency-name: "lm-eval"
     groups:
       patch-update:
         applies-to: version-updates

Dockerfile

@@ -206,7 +206,7 @@ FROM vllm-base AS vllm-openai
 
 # install additional dependencies for openai api server
 RUN --mount=type=cache,target=/root/.cache/pip \
-    pip install accelerate hf_transfer 'modelscope!=1.15.0' bitsandbytes>=0.44.0 timm==0.9.10
+    pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.44.0' timm==0.9.10
 
 ENV VLLM_USAGE_SOURCE production-docker-image
 

Dockerfile.neuron

@@ -31,7 +31,7 @@ RUN --mount=type=bind,source=.git,target=.git \
     if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
 
 RUN python3 -m pip install -U \
-        cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
+        'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
         -r requirements-neuron.txt
 
 ENV VLLM_TARGET_DEVICE neuron

Dockerfile.ppc64le

@@ -21,7 +21,7 @@ RUN --mount=type=bind,source=.git,target=.git \
 # These packages will be in rocketce eventually
 RUN --mount=type=cache,target=/root/.cache/pip  \
     pip install -v --prefer-binary --extra-index-url https://repo.fury.io/mgiessing \
-        cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
+        'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
         torch==2.3.1 \
         -r requirements-cpu.txt \
         xformers uvloop==0.20.0

Dockerfile.rocm

@@ -52,7 +52,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
             python3 -m pip uninstall -y torch torchvision \
             && python3 -m pip install --pre \
                 torch==2.6.0.dev20240918 \
-                setuptools-scm>=8 \
+                'setuptools-scm>=8' \
                 torchvision==0.20.0.dev20240918 \
                 --extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2;; \
         *) ;; esac

Dockerfile.tpu

@@ -25,7 +25,7 @@ ENV VLLM_TARGET_DEVICE="tpu"
 RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=bind,source=.git,target=.git \
     python3 -m pip install \
-        cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
+        'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
         -r requirements-tpu.txt
 RUN python3 setup.py develop
 

docs/requirements-docs.txt

@@ -13,5 +13,7 @@ torch
 py-cpuinfo
 transformers
 mistral_common >= 1.3.4
+aiohttp
+starlette
 openai # Required by docs/source/serving/openai_compatible_server.md's vllm.entrypoints.openai.cli_args
 partial-json-parser # Required by docs/source/serving/openai_compatible_server.md's vllm.entrypoints.openai.cli_args

docs/source/conf.py

@@ -96,7 +96,6 @@ def setup(app):
 
 # Mock out external dependencies here, otherwise the autodoc pages may be blank.
 autodoc_mock_imports = [
-    "aiohttp",
     "compressed_tensors",
     "cpuinfo",
     "cv2",
@@ -143,6 +142,7 @@ def add_line(self, line: str, source: str, *lineno: int) -> None:
     "python": ("https://docs.python.org/3", None),
     "typing_extensions":
     ("https://typing-extensions.readthedocs.io/en/latest", None),
+    "aiohttp": ("https://docs.aiohttp.org/en/stable", None),
     "pillow": ("https://pillow.readthedocs.io/en/stable", None),
     "numpy": ("https://numpy.org/doc/stable", None),
     "torch": ("https://pytorch.org/docs/stable", None),

docs/source/dev/pooling_params.rst

@@ -0,0 +1,5 @@
+Pooling Parameters
+==================
+
+.. autoclass:: vllm.PoolingParams
+    :members:

docs/source/getting_started/quickstart.rst

@@ -138,10 +138,10 @@ Since this server is compatible with OpenAI API, you can use it as a drop-in rep
 
 A more detailed client example can be found `here <https://github.com/vllm-project/vllm/blob/main/examples/openai_completion_client.py>`__.
 
-OpenAI Chat API with vLLM
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+OpenAI Chat Completions API with vLLM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-vLLM is designed to also support the OpenAI Chat API. The chat interface is a more dynamic, interactive way to communicate with the model, allowing back-and-forth exchanges that can be stored in the chat history. This is useful for tasks that require context or more detailed explanations.
+vLLM is designed to also support the OpenAI Chat Completions API. The chat interface is a more dynamic, interactive way to communicate with the model, allowing back-and-forth exchanges that can be stored in the chat history. This is useful for tasks that require context or more detailed explanations.
 
 You can use the `create chat completion <https://platform.openai.com/docs/api-reference/chat/completions/create>`_ endpoint to interact with the model:
 
@@ -157,7 +157,7 @@ You can use the `create chat completion <https://platform.openai.com/docs/api-re
     $         ]
     $     }'
 
-Alternatively, you can use the `openai` python package:
+Alternatively, you can use the ``openai`` python package:
 
 .. code-block:: python
 

docs/source/getting_started/tpu-installation.rst

@@ -1,35 +1,167 @@
 .. _installation_tpu:
 
+#####################
 Installation with TPU
-=====================
+#####################
 
-vLLM supports Google Cloud TPUs using PyTorch XLA.
+Tensor Processing Units (TPUs) are Google's custom-developed application-specific 
+integrated circuits (ASICs) used to accelerate machine learning workloads. TPUs 
+are available in different versions each with different hardware specifications.
+For more information about TPUs, see `TPU System Architecture <https://cloud.google.com/tpu/docs/system-architecture-tpu-vm>`_. 
+For more information on the TPU versions supported with vLLM, see:
+
+* `TPU v6e <https://cloud.google.com/tpu/docs/v6e>`_
+* `TPU v5e <https://cloud.google.com/tpu/docs/v5e>`_
+* `TPU v5p <https://cloud.google.com/tpu/docs/v5p>`_
+* `TPU v4 <https://cloud.google.com/tpu/docs/v4>`_
+
+These TPU versions allow you to configure the physical arrangements of the TPU 
+chips. This can improve throughput and networking performance. For more 
+information see: 
+
+* `TPU v6e topologies <https://cloud.google.com/tpu/docs/v6e#configurations>`_
+* `TPU v5e topologies <https://cloud.google.com/tpu/docs/v5e#tpu-v5e-config>`_
+* `TPU v5p topologies <https://cloud.google.com/tpu/docs/v5p#tpu-v5p-config>`_
+* `TPU v4 topologies <https://cloud.google.com/tpu/docs/v4#tpu-v4-config>`_
+
+In order for you to use Cloud TPUs you need to have TPU quota granted to your 
+Google Cloud Platform project. TPU quotas specify how many TPUs you can use in a
+GPC project and are specified in terms of TPU version, the number of TPU you 
+want to use, and quota type. For more information, see `TPU quota <https://cloud.google.com/tpu/docs/quota#tpu_quota>`_. 
+
+For TPU pricing information, see `Cloud TPU pricing <https://cloud.google.com/tpu/pricing>`_.
+
+You may need additional persistent storage for your TPU VMs. For more 
+information, see `Storage options for Cloud TPU data <https://cloud.devsite.corp.google.com/tpu/docs/storage-options>`_.
 
 Requirements
 ------------
 
-* Google Cloud TPU VM (single & multi host)
-* TPU versions: v5e, v5p, v4
-* Python: 3.10
+* Google Cloud TPU VM 
+* TPU versions: v6e, v5e, v5p, v4
+* Python: 3.10 or newer
+
+Provision Cloud TPUs
+====================
+
+You can provision Cloud TPUs using the `Cloud TPU API <https://cloud.google.com/tpu/docs/reference/rest>`_` 
+or the `queued resources <https://cloud.google.com/tpu/docs/queued-resources>`_` 
+API. This section shows how to create TPUs using the queued resource API. 
+For more information about using the Cloud TPU API, see `Create a Cloud TPU using the Create Node API <https://cloud.google.com/tpu/docs/managing-tpus-tpu-vm#create-node-api>`_. 
+`Queued resources <https://cloud.devsite.corp.google.com/tpu/docs/queued-resources>`_
+enable you to request Cloud TPU resources in a queued manner. When you request 
+queued resources, the request is added to a queue maintained by the Cloud TPU 
+service. When the requested resource becomes available, it's assigned to your 
+Google Cloud project for your immediate exclusive use. 
+
+Provision a Cloud TPU with the queued resource API
+--------------------------------------------------
+Create a TPU v5e with 4 TPU chips:
+
+.. code-block:: console
+
+    gcloud alpha compute tpus queued-resources create QUEUED_RESOURCE_ID \
+    --node-id TPU_NAME \
+    --project PROJECT_ID \
+    --zone ZONE \
+    --accelerator-type ACCELERATOR_TYPE \
+    --runtime-version RUNTIME_VERSION \
+    --service-account SERVICE_ACCOUNT
+
+.. list-table:: Parameter descriptions
+    :header-rows: 1
+
+    * - Parameter name
+      - Description
+    * - QUEUED_RESOURCE_ID
+      - The user-assigned ID of the queued resource request.
+    * - TPU_NAME
+      - The user-assigned name of the TPU which is created when the queued 
+        resource request is allocated.
+    * - PROJECT_ID
+      - Your Google Cloud project
+    * - ZONE
+      - The `zone <https://cloud.google.com/tpu/docs/regions-zones>`_ where you 
+        want to create your Cloud TPU.
+    * - ACCELERATOR_TYPE
+      - The TPU version you want to use. Specify the TPU version, followed by a 
+        '-' and the number of TPU cores. For example `v5e-4` specifies a v5e TPU 
+        with 4 cores. For more information, see `TPU versions <https://cloud.devsite.corp.google.com/tpu/docs/system-architecture-tpu-vm#versions>`_.
+    * - RUNTIME_VERSION
+      - The TPU VM runtime version to use. For more information see `TPU VM images <https://cloud.google.com/tpu/docs/runtimes>`_.
+    * - SERVICE_ACCOUNT
+      - The email address for your service account. You can find it in the IAM 
+        Cloud Console under *Service Accounts*. For example: 
+        `tpu-service-account@<your_project_ID>.iam.gserviceaccount.com`
+
+Connect to your TPU using SSH:
+
+.. code-block:: bash
+
+    gcloud compute tpus tpu-vm ssh TPU_NAME
+
+Create and activate a Conda environment for vLLM:
+
+.. code-block:: bash
 
-Installation options:
+    conda create -n vllm python=3.10 -y
+    conda activate vllm
 
-1. :ref:`Build a docker image with Dockerfile <build_docker_tpu>`.
-2. :ref:`Build from source <build_from_source_tpu>`.
+Clone the vLLM repository and go to the vLLM directory:
+
+.. code-block:: bash
+
+    git clone https://github.com/vllm-project/vllm.git && cd vllm
+
+Uninstall the existing `torch` and `torch_xla` packages:
+
+.. code-block:: bash
+
+    pip uninstall torch torch-xla -y
+
+Install `torch` and `torch_xla`
+
+.. code-block:: bash
+
+    pip install --pre torch==2.6.0.dev20241028+cpu torchvision==0.20.0.dev20241028+cpu --index-url https://download.pytorch.org/whl/nightly/cpu
+    pip install 'torch_xla[tpu] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.6.0.dev-cp310-cp310-linux_x86_64.whl' -f https://storage.googleapis.com/libtpu-releases/index.html
+
+Install JAX and Pallas:
+
+.. code-block:: bash
+
+    pip install torch_xla[pallas] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
+    pip install jaxlib==0.4.32.dev20240829 jax==0.4.32.dev20240829 -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
+
+Install other build dependencies:
+
+.. code-block:: bash
+
+    pip install -r requirements-tpu.txt
+    VLLM_TARGET_DEVICE="tpu" python setup.py develop
+    sudo apt-get install libopenblas-base libopenmpi-dev libomp-dev 
+
+Provision Cloud TPUs with GKE 
+-----------------------------
+
+For more information about using TPUs with GKE, see 
+https://cloud.google.com/kubernetes-engine/docs/how-to/tpus
+https://cloud.google.com/kubernetes-engine/docs/concepts/tpus
+https://cloud.google.com/kubernetes-engine/docs/concepts/plan-tpus
 
 .. _build_docker_tpu:
 
 Build a docker image with :code:`Dockerfile.tpu`
 ------------------------------------------------
 
-`Dockerfile.tpu <https://github.com/vllm-project/vllm/blob/main/Dockerfile.tpu>`_ is provided to build a docker image with TPU support.
+You can use `Dockerfile.tpu <https://github.com/vllm-project/vllm/blob/main/Dockerfile.tpu>`_ 
+to build a Docker image with TPU support.
 
 .. code-block:: console
 
     $ docker build -f Dockerfile.tpu -t vllm-tpu .
 
-
-You can run the docker image with the following command:
+Run the Docker image with the following command:
 
 .. code-block:: console
 
@@ -75,14 +207,12 @@ Next, build vLLM from source. This will only take a few seconds:
 
     $ VLLM_TARGET_DEVICE="tpu" python setup.py develop
 
-
 .. note::
 
     Since TPU relies on XLA which requires static shapes, vLLM bucketizes the possible input shapes and compiles an XLA graph for each different shape.
     The compilation time may take 20~30 minutes in the first run.
     However, the compilation time reduces to ~5 minutes afterwards because the XLA graphs are cached in the disk (in :code:`VLLM_XLA_CACHE_PATH` or :code:`~/.cache/vllm/xla_cache` by default).
 
-
 .. tip::
 
     If you encounter the following error:
@@ -93,7 +223,7 @@ Next, build vLLM from source. This will only take a few seconds:
         ImportError: libopenblas.so.0: cannot open shared object file: No such file or directory
 
 
-    Please install OpenBLAS with the following command:
+    Install OpenBLAS with the following command:
 
     .. code-block:: console
 

docs/source/index.rst

@@ -134,6 +134,7 @@ Documentation
    :caption: Developer Documentation
 
    dev/sampling_params
+   dev/pooling_params
    dev/offline_inference/offline_index
    dev/engine/engine_index
    dev/kernel/paged_attention

docs/source/models/supported_models.rst

@@ -160,13 +160,13 @@ Text Generation
     -
     - ✅︎
   * - :code:`GraniteForCausalLM`
-    - PowerLM
-    - :code:`ibm/PowerLM-3b` etc.
+    - Granite 3.0, PowerLM
+    - :code:`ibm-granite/granite-3.0-2b-base`, :code:`ibm-granite/granite-3.0-8b-instruct`, :code:`ibm/PowerLM-3b`, etc.
     - ✅︎
     - ✅︎
   * - :code:`GraniteMoeForCausalLM`
-    - PowerMoE
-    - :code:`ibm/PowerMoE-3b` etc.
+    - Granite 3.0 MoE, PowerMoE
+    - :code:`ibm-granite/granite-3.0-1b-a400m-base`, :code:`ibm-granite/granite-3.0-3b-a800m-instruct`, :code:`ibm/PowerMoE-3b`, etc.
     - ✅︎
     - ✅︎
   * - :code:`InternLMForCausalLM`
@@ -281,7 +281,7 @@ Text Generation
     - ✅︎
   * - :code:`Qwen2ForCausalLM`
     - Qwen2
-    - :code:`Qwen/Qwen2-beta-7B`, :code:`Qwen/Qwen2-beta-7B-Chat`, etc.
+    - :code:`Qwen/Qwen2-7B-Instruct`, :code:`Qwen/Qwen2-7B`, etc.
     - ✅︎
     - ✅︎
   * - :code:`Qwen2MoeForCausalLM`
@@ -472,7 +472,7 @@ Text Generation
     - ✅︎
   * - :code:`LlavaOnevisionForConditionalGeneration`
     - LLaVA-Onevision
-    - T + I\ :sup:`+` + V
+    - T + I\ :sup:`+` + V\ :sup:`+`
     - :code:`llava-hf/llava-onevision-qwen2-7b-ov-hf`, :code:`llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc.
     -
     - ✅︎
@@ -484,7 +484,7 @@ Text Generation
     - ✅︎
   * - :code:`MllamaForConditionalGeneration`
     - Llama 3.2
-    - T + I
+    - T + I\ :sup:`+`
     - :code:`meta-llama/Llama-3.2-90B-Vision-Instruct`, :code:`meta-llama/Llama-3.2-11B-Vision`, etc.
     -
     -