Upgrade FlashInfer to v0.2.11 (vllm-project#22613)

Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Paul Pak <[email protected]>

Author: 2 people

docker/Dockerfile

@@ -387,7 +387,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
 ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
 # Keep this in sync with https://github.com/vllm-project/vllm/blob/main/requirements/cuda.txt
 # We use `--force-reinstall --no-deps` to avoid issues with the existing FlashInfer wheel.
-ARG FLASHINFER_GIT_REF="v0.2.10"
+ARG FLASHINFER_GIT_REF="v0.2.11"
 RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
   . /etc/environment
     git clone --depth 1 --recursive --shallow-submodules \

setup.py

@@ -684,7 +684,7 @@ def _read_requirements(filename: str) -> list[str]:
                   "mistral_common[audio]"],  # Required for audio processing
         "video": [],  # Kept for backwards compatibility
         # FlashInfer should be updated together with the Dockerfile
-        "flashinfer": ["flashinfer-python==0.2.10"],
+        "flashinfer": ["flashinfer-python==0.2.11"],
     },
     cmdclass=cmdclass,
     package_data=package_data,