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 7, 09:00 UTC
[CI/Build] Allow mounting AWS credentials for sccache S3 auth (#35912)
Signed-off-by: Amr Mahdi <amrmahdi@meta.com>
Amr Mahdi committed
Mar 3, 2026 at 14:30 UTC
12b38c0f4560e33b32cd5fbe50881d4d2e97470e
1 file changed
+2
docker/Dockerfile
+2
@@ -262,7 +262,9 @@ RUN --mount=type=cache,target=/root/.cache/uv \
262
263
# Build the vLLM wheel
264
# if USE_SCCACHE is set, use sccache to speed up compilation
265
+# AWS credentials mounted at ~/.aws/credentials for sccache S3 auth (optional)
266
RUN --mount=type=cache,target=/root/.cache/uv \
267
+ --mount=type=secret,id=aws-credentials,target=/root/.aws/credentials,required=false \
268
if [ "$USE_SCCACHE" = "1" ]; then \
269
echo "Installing sccache..." \
270
&& case "${TARGETPLATFORM}" in \