Merge remote-tracking branch 'mirror/releases/v0.9.0' into v0.9.0-ori

docker/Dockerfile.neuron

 # default base image
 # https://gallery.ecr.aws/neuron/pytorch-inference-neuronx
-ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.5.1-neuronx-py310-sdk2.22.0-ubuntu22.04"
+ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.6.0-neuronx-py310-sdk2.23.0-ubuntu22.04"
 
 FROM $BASE_IMAGE
 
@@ -22,8 +22,7 @@ WORKDIR ${APP_MOUNT}/vllm
 
 RUN python3 -m pip install --upgrade pip
 RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas tenacity
-RUN python3 -m pip install sentencepiece transformers==4.48.0 -U
-RUN python3 -m pip install neuronx-cc==2.17.194.0 --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
+RUN python3 -m pip install neuronx-cc==2.* --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
 RUN python3 -m pip install pytest
 
 # uninstall transformers-neuronx package explicitly to avoid version conflict
@@ -49,6 +48,8 @@ RUN python3 -m pip install -e tests/vllm_test_utils
 # FIXME: `--no-deps` argument is temporarily added to resolve transformers package version conflict
 RUN python3 -m pip install transformers-neuronx==0.13.* --extra-index-url=https://pip.repos.neuron.amazonaws.com -U --no-deps
 
+RUN python3 -m pip install sentencepiece transformers==4.48.0 -U
+
 # overwrite entrypoint to run bash script
 RUN echo "import subprocess; import sys; subprocess.check_call(sys.argv[1:])" > /usr/local/bin/dockerd-entrypoint.py
 

docker/Dockerfile.rocm_base

@@ -12,7 +12,7 @@ ARG PYTORCH_REPO="https://github.com/pytorch/pytorch.git"
 ARG PYTORCH_VISION_REPO="https://github.com/pytorch/vision.git"
 ARG FA_BRANCH="1a7f4dfa"
 ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
-ARG AITER_BRANCH="5a77249"
+ARG AITER_BRANCH="c1debd8"
 ARG AITER_REPO="https://github.com/ROCm/aiter.git"
 
 FROM ${BASE_IMAGE} AS base

docker/Dockerfile.s390x

@@ -84,16 +84,40 @@ RUN curl https://sh.rustup.rs -sSf | sh -s -- -y && \
     rustup default stable && \
     rustup show
 
+FROM python-install AS torch
+ARG TORCH_VERSION=2.7.0
+ENV export _GLIBCXX_USE_CXX11_ABI=1
+ENV CARGO_HOME=/root/.cargo
+ENV RUSTUP_HOME=/root/.rustup
+ENV PATH="$CARGO_HOME/bin:$RUSTUP_HOME/bin:$PATH"
+
+WORKDIR /tmp
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,from=rust,source=/root/.cargo,target=/root/.cargo,rw \
+    --mount=type=bind,from=rust,source=/root/.rustup,target=/root/.rustup,rw \
+    git clone https://github.com/pytorch/pytorch.git && \
+    cd pytorch && \
+    git checkout v2.7.0 && \
+    git submodule sync && \
+    git submodule update --init --recursive && \
+    uv pip install cmake ninja && \
+    uv pip install -r requirements.txt && \
+    python setup.py bdist_wheel
+    
+
 FROM python-install AS torch-vision
 # Install torchvision
-ARG TORCH_VERSION=2.7.0.dev20250304
+ARG TORCH_VERSION=2.7.0
 ARG TORCH_VISION_VERSION=v0.20.1
 WORKDIR /tmp
 RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,from=torch,source=/tmp/pytorch/dist,target=/tmp/torch-wheels/ \
     git clone https://github.com/pytorch/vision.git && \
     cd vision && \
     git checkout $TORCH_VISION_VERSION && \
-    uv pip install -v torch==${TORCH_VERSION} --extra-index-url https://download.pytorch.org/whl/nightly/cpu && \
+    TORCH_WHL_FILE=$(ls /tmp/torch-wheels/*.whl | head -n 1) && \
+    uv pip install -v $TORCH_WHL_FILE && \
     python setup.py bdist_wheel
 
 FROM python-install AS hf-xet-builder
@@ -138,15 +162,17 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,from=pyarrow,source=/tmp/arrow/python/dist,target=/tmp/arrow-wheels \
     --mount=type=bind,from=torch-vision,source=/tmp/vision/dist,target=/tmp/vision-wheels/ \
     --mount=type=bind,from=hf-xet-builder,source=/tmp/hf-xet/dist,target=/tmp/hf-xet-wheels/ \
+    --mount=type=bind,from=torch,source=/tmp/pytorch/dist,target=/tmp/torch-wheels/ \
      sed -i '/^torch/d' requirements/build.txt && \
      ARROW_WHL_FILE=$(ls /tmp/arrow-wheels/pyarrow-*.whl | head -n 1) && \
      VISION_WHL_FILE=$(ls /tmp/vision-wheels/*.whl | head -n 1) && \
      HF_XET_WHL_FILE=$(ls /tmp/hf-xet-wheels/*.whl | head -n 1) && \
+     TORCH_WHL_FILE=$(ls /tmp/torch-wheels/*.whl | head -n 1) && \
     uv pip install -v \    
         $ARROW_WHL_FILE  \
         $VISION_WHL_FILE \
         $HF_XET_WHL_FILE \
-        --extra-index-url https://download.pytorch.org/whl/nightly/cpu \
+        $TORCH_WHL_FILE \
         --index-strategy unsafe-best-match \
         -r requirements/build.txt \
         -r requirements/cpu.txt 

docs/.nav.yml

+nav:
+  - Home: 
+    - vLLM: README.md
+    - Getting Started:
+      - getting_started/quickstart.md
+      - getting_started/installation
+    - Examples:
+      - Offline Inference: examples/offline_inference
+      - Online Serving: examples/online_serving
+      - Others: examples/others
+    - Quick Links:
+      - User Guide: usage/README.md
+      - Developer Guide: contributing/README.md
+      - API Reference: api/README.md
+    - Timeline:
+      - Roadmap: https://roadmap.vllm.ai
+      - Releases: https://github.com/vllm-project/vllm/releases
+  - User Guide:
+    - Summary: usage/README.md
+    - usage/v1_guide.md
+    - General:
+      - usage/*
+    - Inference and Serving:
+      - serving/offline_inference.md
+      - serving/openai_compatible_server.md
+      - serving/*
+      - serving/integrations
+    - Deployment:
+      - deployment/*
+      - deployment/frameworks
+      - deployment/integrations
+    - Training: training
+    - Configuration:
+      - Summary: configuration/README.md
+      - configuration/*
+    - Models:
+      - models/supported_models.md
+      - models/generative_models.md
+      - models/pooling_models.md
+      - models/extensions
+    - Features:
+      - features/compatibility_matrix.md
+      - features/*
+      - features/quantization
+  - Developer Guide:
+    - Summary: contributing/README.md
+    - General:
+      - glob: contributing/*
+        flatten_single_child_sections: true
+    - Model Implementation: contributing/model
+    - Design Documents:
+      - V0: design
+      - V1: design/v1
+  - API Reference:
+    - Summary: api/README.md
+    - Contents:
+      - glob: api/vllm/*
+        preserve_directory_names: true
+  - Community:
+    - community/*
+    - Blog: https://blog.vllm.ai
+    - Forum: https://discuss.vllm.ai
+    - Slack: https://slack.vllm.ai

docs/Makefile

-# Minimal makefile for Sphinx documentation
-#
-
-# You can set these variables from the command line, and also
-# from the environment for the first two.
-SPHINXOPTS    ?=
-SPHINXBUILD   ?= sphinx-build
-SOURCEDIR     = source
-BUILDDIR      = build
-
-# Put it first so that "make" without argument is like "make help".
-help:
-	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
-
-.PHONY: help Makefile
-
-# Catch-all target: route all unknown targets to Sphinx using the new
-# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
-%: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
-
-clean:
-	@$(SPHINXBUILD) -M clean "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
-	rm -rf "$(SOURCEDIR)/getting_started/examples"
-	rm -rf "$(SOURCEDIR)/api/vllm"

docs/README.md

-# vLLM documents
-
-## Build the docs
-
-- Make sure in `docs` directory
-
-```bash
-cd docs
-```
-
-- Install the dependencies:
-
-```bash
-pip install -r ../requirements/docs.txt
-```
-
-- Clean the previous build (optional but recommended):
-
-```bash
-make clean
-```
-
-- Generate the HTML documentation:
-
-```bash
-make html
-```
-
-## Open the docs with your browser
-
-- Serve the documentation locally:
-
-```bash
-python -m http.server -d build/html/
-```
-
-This will start a local server at http://localhost:8000. You can now open your browser and view the documentation.
-
-If port 8000 is already in use, you can specify a different port, for example:
-
-```bash
-python -m http.server 3000 -d build/html/
-```
+# Welcome to vLLM
+
+<figure markdown="span">
+  ![](./assets/logos/vllm-logo-text-light.png){ align="center" alt="vLLM" class="no-scaled-link" width="60%" }
+</figure>
+
+<p style="text-align:center">
+<strong>Easy, fast, and cheap LLM serving for everyone
+</strong>
+</p>
+
+<p style="text-align:center">
+<script async defer src="https://buttons.github.io/buttons.js"></script>
+<a class="github-button" href="https://github.com/vllm-project/vllm" data-show-count="true" data-size="large" aria-label="Star">Star</a>
+<a class="github-button" href="https://github.com/vllm-project/vllm/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
+<a class="github-button" href="https://github.com/vllm-project/vllm/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
+</p>
+
+vLLM is a fast and easy-to-use library for LLM inference and serving.
+
+Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu) at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
+
+vLLM is fast with:
+
+- State-of-the-art serving throughput
+- Efficient management of attention key and value memory with [**PagedAttention**](https://blog.vllm.ai/2023/06/20/vllm.html)
+- Continuous batching of incoming requests
+- Fast model execution with CUDA/HIP graph
+- Quantization: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), INT4, INT8, and FP8
+- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer.
+- Speculative decoding
+- Chunked prefill
+
+vLLM is flexible and easy to use with:
+
+- Seamless integration with popular HuggingFace models
+- High-throughput serving with various decoding algorithms, including *parallel sampling*, *beam search*, and more
+- Tensor parallelism and pipeline parallelism support for distributed inference
+- Streaming outputs
+- OpenAI-compatible API server
+- Support NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs, Gaudi® accelerators and GPUs, IBM Power CPUs, TPU, and AWS Trainium and Inferentia Accelerators.
+- Prefix caching support
+- Multi-lora support
+
+For more information, check out the following:
+
+- [vLLM announcing blog post](https://vllm.ai) (intro to PagedAttention)
+- [vLLM paper](https://arxiv.org/abs/2309.06180) (SOSP 2023)
+- [How continuous batching enables 23x throughput in LLM inference while reducing p50 latency](https://www.anyscale.com/blog/continuous-batching-llm-inference) by Cade Daniel et al.
+- [vLLM Meetups][meetups]

docs/api/README.md

+# Summary
+
+[](){ #configuration }
+
+## Configuration
+
+API documentation for vLLM's configuration classes.
+
+- [vllm.config.ModelConfig][]
+- [vllm.config.CacheConfig][]
+- [vllm.config.TokenizerPoolConfig][]
+- [vllm.config.LoadConfig][]
+- [vllm.config.ParallelConfig][]
+- [vllm.config.SchedulerConfig][]
+- [vllm.config.DeviceConfig][]
+- [vllm.config.SpeculativeConfig][]
+- [vllm.config.LoRAConfig][]
+- [vllm.config.PromptAdapterConfig][]
+- [vllm.config.MultiModalConfig][]
+- [vllm.config.PoolerConfig][]
+- [vllm.config.DecodingConfig][]
+- [vllm.config.ObservabilityConfig][]
+- [vllm.config.KVTransferConfig][]
+- [vllm.config.CompilationConfig][]
+- [vllm.config.VllmConfig][]
+
+[](){ #offline-inference-api }
+
+## Offline Inference
+
+LLM Class.
+
+- [vllm.LLM][]
+
+LLM Inputs.
+
+- [vllm.inputs.PromptType][]
+- [vllm.inputs.TextPrompt][]
+- [vllm.inputs.TokensPrompt][]
+
+## vLLM Engines
+
+Engine classes for offline and online inference.
+
+- [vllm.LLMEngine][]
+- [vllm.AsyncLLMEngine][]
+
+## Inference Parameters
+
+Inference parameters for vLLM APIs.
+
+[](){ #sampling-params }
+[](){ #pooling-params }
+
+- [vllm.SamplingParams][]
+- [vllm.PoolingParams][]
+
+[](){ #multi-modality }
+
+## Multi-Modality
+
+vLLM provides experimental support for multi-modal models through the [vllm.multimodal][] package.
+
+Multi-modal inputs can be passed alongside text and token prompts to [supported models][supported-mm-models]
+via the `multi_modal_data` field in [vllm.inputs.PromptType][].
+
+Looking to add your own multi-modal model? Please follow the instructions listed [here][supports-multimodal].
+
+- [vllm.multimodal.MULTIMODAL_REGISTRY][]
+
+### Inputs
+
+User-facing inputs.
+
+- [vllm.multimodal.inputs.MultiModalDataDict][]
+
+Internal data structures.
+
+- [vllm.multimodal.inputs.PlaceholderRange][]
+- [vllm.multimodal.inputs.NestedTensors][]
+- [vllm.multimodal.inputs.MultiModalFieldElem][]
+- [vllm.multimodal.inputs.MultiModalFieldConfig][]
+- [vllm.multimodal.inputs.MultiModalKwargsItem][]
+- [vllm.multimodal.inputs.MultiModalKwargs][]
+- [vllm.multimodal.inputs.MultiModalInputs][]
+
+### Data Parsing
+
+- [vllm.multimodal.parse][]
+
+### Data Processing
+
+- [vllm.multimodal.processing][]
+
+### Memory Profiling
+
+- [vllm.multimodal.profiling][]
+
+### Registry
+
+- [vllm.multimodal.registry][]
+
+## Model Development
+
+- [vllm.model_executor.models.interfaces_base][]
+- [vllm.model_executor.models.interfaces][]
+- [vllm.model_executor.models.adapters][]

docs/api/vllm/.meta.yml

+search:
+  boost: 0.5