Merge tag 'v0.5.5' into v0.5.5-dtk24.04.1

af7f4372 · zhuwenwen · 5e19cdef · 09c77926 · af7f4372 · af7f4372
Commit af7f4372 authored Sep 03, 2024 by zhuwenwen
20 changed files
--- a/csrc/quantization/machete/machete_mainloop.cuh
+++ b/csrc/quantization/machete/machete_mainloop.cuh
--- a/csrc/quantization/machete/machete_mm_kernel.cuh
+++ b/csrc/quantization/machete/machete_mm_kernel.cuh
--- a/csrc/quantization/machete/machete_mm_launcher.cuh
+++ b/csrc/quantization/machete/machete_mm_launcher.cuh
--- a/csrc/quantization/machete/machete_prepack_kernel.cuh
+++ b/csrc/quantization/machete/machete_prepack_kernel.cuh
--- a/csrc/quantization/machete/machete_prepack_launcher.cuh
+++ b/csrc/quantization/machete/machete_prepack_launcher.cuh
--- a/csrc/quantization/machete/machete_prepacked_layout.cuh
+++ b/csrc/quantization/machete/machete_prepacked_layout.cuh
--- a/csrc/quantization/machete/machete_pytorch.cu
+++ b/csrc/quantization/machete/machete_pytorch.cu
--- a/csrc/reduction_utils.cuh
+++ b/csrc/reduction_utils.cuh
--- a/csrc/torch_bindings.cpp
+++ b/csrc/torch_bindings.cpp
--- a/docs/requirements-docs.txt
+++ b/docs/requirements-docs.txt
@@ -3,9 +3,10 @@ sphinx-book-theme==1.0.1
 sphinx-copybutton==0.5.2
 myst-parser==2.0.0
 sphinx-argparse==0.4.0
+msgspec

 # packages to install to build the documentation
-pydantic
+pydantic >= 2.8
 -f https://download.pytorch.org/whl/cpu
 torch
 py-cpuinfo

--- a/docs/source/community/sponsors.md
+++ b/docs/source/community/sponsors.md
@@ -20,6 +20,7 @@ vLLM is a community project. Our compute resources for development and testing a
 - Roblox
 - RunPod
 - Sequoia Capital
+- Skywork AI
 - Trainy
 - UC Berkeley
 - UC San Diego

--- a/docs/source/conf.py
+++ b/docs/source/conf.py
--- a/docs/source/dev/input_processing/input_processing_pipeline.rst
+++ b/docs/source/dev/input_processing/input_processing_pipeline.rst
@@ -17,4 +17,4 @@ Input Processing Pipeline

 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 language model.
+   - For example, convert a :class:`PIL.Image.Image` input to its pixel values for a vision model.
--- a/docs/source/dev/multimodal/multimodal_index.rst
+++ b/docs/source/dev/multimodal/multimodal_index.rst
--- a/docs/source/dev/profiling/profiling_index.rst
+++ b/docs/source/dev/profiling/profiling_index.rst
--- a/docs/source/getting_started/debugging.rst
+++ b/docs/source/getting_started/debugging.rst
--- a/docs/source/getting_started/installation.rst
+++ b/docs/source/getting_started/installation.rst
--- a/docs/source/getting_started/openvino-installation.rst
+++ b/docs/source/getting_started/openvino-installation.rst
--- a/docs/source/getting_started/tpu-installation.rst
+++ b/docs/source/getting_started/tpu-installation.rst
--- a/docs/source/index.rst
+++ b/docs/source/index.rst