@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / c09503ddd6
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

[AMD][CI/Build][Bugfix] use pytorch stale wheel (#12172)

Signed-off-by: hongxyan <hongxyan@amd.com>

Hongxia Yang committed Jan 17, 2025 at 22:15 UTC c09503ddd657850c66548b5bb28e58bac1c4afb7
2 files changed +4 -4
Dockerfile.rocm
+3 -3
@@ -51,10 +51,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
51 *"rocm-6.2"*) \
52 python3 -m pip uninstall -y torch torchvision \
53 && python3 -m pip install --pre \
54 - torch==2.6.0.dev20241113+rocm6.2 \
54 + torch \
55 'setuptools-scm>=8' \
56 - torchvision==0.20.0.dev20241113+rocm6.2 \
57 - --extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2;; \
56 + torchvision \
57 + --extra-index-url https://download.pytorch.org/whl/rocm6.2;; \
58 *) ;; esac
59
60 ENV LLVM_SYMBOLIZER_PATH=/opt/rocm/llvm/bin/llvm-symbolizer
docs/source/getting_started/installation/gpu/rocm.inc.md
+1 -1
@@ -70,7 +70,7 @@ Currently, there are no pre-built ROCm wheels.
70
71 # Install PyTorch
72 $ pip uninstall torch -y
73 - $ pip install --no-cache-dir --pre torch==2.6.0.dev20241024 --index-url https://download.pytorch.org/whl/nightly/rocm6.2
73 + $ pip install --no-cache-dir --pre torch --index-url https://download.pytorch.org/whl/rocm6.2
74
75 # Build & install AMD SMI
76 $ pip install /opt/rocm/share/amd_smi