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 16, 02:00 UTC
[Bugfix] Fixing AMD LoRA CI test. (#12329)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
Alexei-V-Ivanov-AMD committed
Jan 22, 2025 at 20:53 UTC
8d7aa9de718d55dd5e17846c6a88f3cd11c138d4
1 file changed
+2
-1
Dockerfile.rocm
+2
-1
@@ -72,7 +72,8 @@ COPY --from=build_vllm ${COMMON_WORKDIR}/vllm /vllm-workspace
72
RUN cd /vllm-workspace \
73
&& rm -rf vllm \
74
&& python3 -m pip install -e tests/vllm_test_utils \
75
- && python3 -m pip install lm-eval[api]==0.4.4
75
+ && python3 -m pip install lm-eval[api]==0.4.4 \
76
+ && python3 -m pip install pytest-shard
77
78
# -----------------------
79
# Final vLLM image