A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 9, 10:00 UTC
[CI/Build][BugFix] fix cuda/compat loading order issue in docker build (#33116)
Signed-off-by: Pengchao Wang <wpc@fb.com> Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Pengchao Wang committed
Jan 29, 2026 at 00:19 UTC
2515bbd02798a0f736a82bbdd10dbf9d5accfa7c
1 file changed
+2
-2
docker/Dockerfile
+2
-2
@@ -135,7 +135,7 @@ ENV UV_LINK_MODE=copy
135
RUN gcc --version
136
137
# Ensure CUDA compatibility library is loaded
138
-RUN echo "/usr/local/cuda-$(echo "$CUDA_VERSION" | cut -d. -f1,2)/compat/" > /etc/ld.so.conf.d/00-cuda-compat.conf && ldconfig
138
+RUN echo "/usr/local/cuda-$(echo "$CUDA_VERSION" | cut -d. -f1,2)/compat/" > /etc/ld.so.conf.d/cuda-compat.conf && ldconfig
139
140
# ============================================================
141
# SLOW-CHANGING DEPENDENCIES BELOW
@@ -565,7 +565,7 @@ ENV UV_INDEX_STRATEGY="unsafe-best-match"
565
ENV UV_LINK_MODE=copy
566
567
# Ensure CUDA compatibility library is loaded
568
-RUN echo "/usr/local/cuda-$(echo "$CUDA_VERSION" | cut -d. -f1,2)/compat/" > /etc/ld.so.conf.d/00-cuda-compat.conf && ldconfig
568
+RUN echo "/usr/local/cuda-$(echo "$CUDA_VERSION" | cut -d. -f1,2)/compat/" > /etc/ld.so.conf.d/cuda-compat.conf && ldconfig
569
570
# ============================================================
571
# SLOW-CHANGING DEPENDENCIES BELOW