update to 0.4.0

Author: elvischenv

docker/Dockerfile

@@ -371,7 +371,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
 # Install FlashInfer from source
 ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
 # Keep this in sync with "flashinfer" extra in setup.py
-ARG FLASHINFER_GIT_REF="v0.4.0rc4"
+ARG FLASHINFER_GIT_REF="v0.4.0"
 # Flag to control whether to compile FlashInfer AOT kernels
 # Set to "true" to enable AOT compilation:
 # docker build --build-arg FLASHINFER_AOT_COMPILE=true ...

docker/Dockerfile.nightly_torch

@@ -246,15 +246,15 @@ 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: v0.4.0rc4
+# release version: v0.4.0
 # 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 --recursive https://github.com/flashinfer-ai/flashinfer.git \
     && cd flashinfer \
-    && git checkout v0.4.0rc4 \
+    && git checkout v0.4.0 \
     && git submodule update --init --recursive \
     && echo "finish git clone flashinfer..." \
     && rm -rf build \

setup.py

@@ -715,7 +715,7 @@ def _read_requirements(filename: str) -> list[str]:
         ],  # Required for audio processing
         "video": [],  # Kept for backwards compatibility
         # FlashInfer should be updated together with the Dockerfile
-        "flashinfer": ["flashinfer-python==0.4.0rc4"],
+        "flashinfer": ["flashinfer-python==0.4.0"],
         # Optional deps for AMD FP4 quantization support
         "petit-kernel": ["petit-kernel"],
     },