biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

cherry-pick [CI Bugfix] Pre-download missing FlashInfer headers in Docker build

Browse Source 
Signed-off-by: khluu <khluu000@gmail.com>
#38391
This commit is contained in:
Michael Goin
2026-03-27 14:34:30 -07:00
committed by khluu
parent 9fdc0f3aeb
commit d1b4f10b19
1 changed files with 19 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
docker/Dockerfile
View File

@@ -593,6 +593,25 @@ RUN --mount=type=cache,target=/root/.cache/uv \
--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
# Pre-download FlashInfer TRTLLM BMM headers for air-gapped environments.
# At runtime, MoE JIT compilation downloads these from edge.urm.nvidia.com
# which fails without internet. This step caches them at build time.
RUN python3 <<'PYEOF'
from flashinfer.jit import env as jit_env
from flashinfer.jit.cubin_loader import download_trtllm_headers, get_cubin
from flashinfer.artifacts import ArtifactPath, CheckSumHash
download_trtllm_headers(
'bmm',
jit_env.FLASHINFER_CUBIN_DIR / 'flashinfer' / 'trtllm' / 'batched_gemm' / 'trtllmGen_bmm_export',
f'{ArtifactPath.TRTLLM_GEN_BMM}/include/trtllmGen_bmm_export',
ArtifactPath.TRTLLM_GEN_BMM,
get_cubin(f'{ArtifactPath.TRTLLM_GEN_BMM}/checksums.txt', CheckSumHash.TRTLLM_GEN_BMM),
)
print('FlashInfer TRTLLM BMM headers downloaded successfully')
PYEOF
# ============================================================ # ============================================================
# OPENAI API SERVER DEPENDENCIES # OPENAI API SERVER DEPENDENCIES
# Pre-install these to avoid reinstalling on every vLLM wheel rebuild # Pre-install these to avoid reinstalling on every vLLM wheel rebuild