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 14, 05:30 UTC
[CI/Build] Fix AMD import failures in CI (#26841)
Signed-off-by: zhewenli <zhewenli@meta.com>
Zhewen Li committed
Oct 16, 2025 at 00:28 UTC
44c85556216bb24ab5ccf410dbb2bcfc25c85dd5
2 files changed
+3
-1
docker/Dockerfile.rocm
+1
-1
@@ -12,7 +12,7 @@ ENV PYTORCH_ROCM_ARCH=${ARG_PYTORCH_ROCM_ARCH:-${PYTORCH_ROCM_ARCH}}
12
RUN apt-get update -q -y && apt-get install -q -y \
13
sqlite3 libsqlite3-dev libfmt-dev libmsgpack-dev libsuitesparse-dev \
14
apt-transport-https ca-certificates wget curl
15
-# Remove sccache
15
+# Remove sccache
16
RUN python3 -m pip install --upgrade pip
17
RUN apt-get purge -y sccache; python3 -m pip uninstall -y sccache; rm -f "$(which sccache)"
18
ARG COMMON_WORKDIR
requirements/rocm-test.txt
+2
@@ -29,4 +29,6 @@ matplotlib==3.10.3
29
# Multi-Modal Models Test (Extended) 3
30
blobfile==3.0.0
31
32
+schemathesis==3.39.15 # Required for openai schema test.
33
34
+mteb[bm25s]>=1.38.11, <2 # required for mteb test