@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 8d7aa9de71
Fork 0

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