diff --git a/docker/Dockerfile b/docker/Dockerfile index 06cdc0b667f..1f8476a8fdf 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -757,7 +757,7 @@ RUN --mount=type=cache,target=/opt/uv/cache \ # Install FlashInfer JIT cache (requires CUDA-version-specific index URL) # https://docs.flashinfer.ai/installation.html # From versions.json: .flashinfer.version -ARG FLASHINFER_VERSION=0.6.11.post2 +ARG FLASHINFER_VERSION=0.6.12 RUN --mount=type=cache,target=/opt/uv/cache \ 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 '.') diff --git a/docker/Dockerfile.nightly_torch b/docker/Dockerfile.nightly_torch index 0d5a9cc5f83..4fbfe832ac3 100644 --- a/docker/Dockerfile.nightly_torch +++ b/docker/Dockerfile.nightly_torch @@ -256,13 +256,13 @@ 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 -# release version: v0.6.11.post2 +# release version: v0.6.12 # todo(elainewy): cache flashinfer build result for faster build ENV CCACHE_DIR=/root/.cache/ccache RUN --mount=type=cache,target=/root/.cache/ccache \ --mount=type=cache,target=/root/.cache/uv \ echo "git clone flashinfer..." \ - && git clone --depth 1 --branch v0.6.11.post2 --recursive https://github.com/flashinfer-ai/flashinfer.git \ + && git clone --depth 1 --branch v0.6.12 --recursive https://github.com/flashinfer-ai/flashinfer.git \ && cd flashinfer \ && git submodule update --init --recursive \ && echo "finish git clone flashinfer..." \ diff --git a/docker/versions.json b/docker/versions.json index ee23b5baf04..15f77648a9c 100644 --- a/docker/versions.json +++ b/docker/versions.json @@ -68,7 +68,7 @@ "default": "true" }, "FLASHINFER_VERSION": { - "default": "0.6.11.post2" + "default": "0.6.12" }, "GDRCOPY_CUDA_VERSION": { "default": "12.8" diff --git a/requirements/cuda.txt b/requirements/cuda.txt index 99a45c9d3ca..b0e16d11c75 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -9,8 +9,8 @@ torchaudio==2.11.0 # These must be updated alongside torch torchvision==0.26.0 # 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-python==0.6.11.post2 -flashinfer-cubin==0.6.11.post2 +flashinfer-python==0.6.12 +flashinfer-cubin==0.6.12 apache-tvm-ffi==0.1.9 tilelang==0.1.9 # Cap nvidia-cudnn-frontend (transitive dep of flashinfer) due to