[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714)

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

docker/Dockerfile

@@ -359,8 +359,8 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
 # Install FlashInfer pre-compiled kernel cache and binaries
 # https://docs.flashinfer.ai/installation.html
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv pip install --system flashinfer-cubin==0.4.0 \
-    && uv pip install --system flashinfer-jit-cache==0.4.0 \
+    uv pip install --system flashinfer-cubin==0.4.1 \
+    && uv pip install --system flashinfer-jit-cache==0.4.1 \
         --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
     && flashinfer show-config
 

docker/Dockerfile.nightly_torch

@@ -246,7 +246,7 @@ 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: v0.4.0
+# release version: v0.4.1
 # todo(elainewy): cache flashinfer build result for faster build
 ENV CCACHE_DIR=/root/.cache/ccache
 RUN --mount=type=cache,target=/root/.cache/ccache \
@@ -254,7 +254,7 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
     echo "git clone flashinfer..." \
     && git clone --recursive https://github.com/flashinfer-ai/flashinfer.git \
     && cd flashinfer \
-    && git checkout v0.4.0 \
+    && git checkout v0.4.1\
     && git submodule update --init --recursive \
     && echo "finish git clone flashinfer..." \
     && rm -rf build \