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 15, 07:15 UTC
[AMD] Update compatible packaging version (#19309)
Signed-off-by: pramkuma <Pramendra.Kumar@amd.com>
pramenku committed
Jun 7, 2025 at 18:25 UTC
88be823d572a773643c8326d13b8e4ee7bf8b1dd
2 files changed
+3
-2
docker/Dockerfile.rocm
+1
-1
@@ -13,7 +13,7 @@ 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
16
-RUN python3 -m pip install --upgrade pip && pip install setuptools_scm
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
19
WORKDIR ${COMMON_WORKDIR}
requirements/rocm.txt
+2
-1
@@ -12,7 +12,8 @@ ray>=2.10.0,<2.45.0
12
peft
13
pytest-asyncio
14
tensorizer>=2.9.0
15
-setuptools-scm>=8
15
+packaging>=24.2
16
setuptools>=77.0.3,<80.0.0
17
+setuptools-scm>=8
18
runai-model-streamer==0.11.0
19
runai-model-streamer-s3==0.11.0