xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-16 16:02:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

bump flashinfer to v0.6.0rc1

Browse Source 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
This commit is contained in:
elvischenv 2025-12-18 13:57:58 -08:00
parent d6b3d39b6d
commit 769f0918ea
3 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docker/Dockerfile
View File

@ -466,9 +466,10 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# Install FlashInfer pre-compiled kernel cache and binaries # Install FlashInfer pre-compiled kernel cache and binaries
# This is ~1.1GB and only changes when FlashInfer version bumps # This is ~1.1GB and only changes when FlashInfer version bumps
# https://docs.flashinfer.ai/installation.html # https://docs.flashinfer.ai/installation.html
ARG FLASHINFER_VERSION=0.5.3 ARG FLASHINFER_VERSION=0.6.0rc1
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system flashinfer-cubin==${FLASHINFER_VERSION} \ uv pip install --system flashinfer-cubin==${FLASHINFER_VERSION} \
--extra-index-url https://flashinfer.ai/whl \
&& uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} \ && uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} \
--extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \ --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
&& flashinfer show-config && flashinfer show-config

5
docker/Dockerfile.nightly_torch
View File

@ -213,15 +213,14 @@ RUN pip install setuptools==75.6.0 packaging==23.2 ninja==1.11.1.3 build==1.2.2.
# build flashinfer for torch nightly from source around 10 mins # build flashinfer for torch nightly from source around 10 mins
# release version: v0.5.2 # release version: v0.6.0rc1
# todo(elainewy): cache flashinfer build result for faster build # todo(elainewy): cache flashinfer build result for faster build
ENV CCACHE_DIR=/root/.cache/ccache ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \ RUN --mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/uv \ --mount=type=cache,target=/root/.cache/uv \
echo "git clone flashinfer..." \ echo "git clone flashinfer..." \
&& git clone --recursive https://github.com/flashinfer-ai/flashinfer.git \ && git clone --depth 1 --branch v0.6.0rc1 --recursive https://github.com/flashinfer-ai/flashinfer.git \
&& cd flashinfer \ && cd flashinfer \
&& git checkout v0.5.2 \
&& git submodule update --init --recursive \ && git submodule update --init --recursive \
&& echo "finish git clone flashinfer..." \ && echo "finish git clone flashinfer..." \
&& rm -rf build \ && rm -rf build \

2
requirements/cuda.txt
View File

@ -10,4 +10,4 @@ torchaudio==2.9.1
# These must be updated alongside torch # These must be updated alongside torch
torchvision==0.24.1 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version torchvision==0.24.1 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
# FlashInfer should be updated together with the Dockerfile # FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.5.3 flashinfer-python==0.6.0rc1