@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / ced36cd89b
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, 20:45 UTC

[ROCm] Upgrade PyTorch nightly version (#6845)

Woosuk Kwon committed Jul 26, 2024 at 20:16 UTC ced36cd89b9c012eb066ef863b2d1ecf052f3e00
2 files changed +3 -3
Dockerfile.rocm
+2 -2
@@ -55,8 +55,8 @@ RUN case "$(ls /opt | grep -Po 'rocm-[0-9]\.[0-9]')" in \
55 *"rocm-6.1"*) \
56 python3 -m pip uninstall -y torch torchvision \
57 && python3 -m pip install --no-cache-dir --pre \
58 - torch==2.5.0.dev20240710 \
59 - torchvision==0.20.0.dev20240710 \
58 + torch==2.5.0.dev20240726 \
59 + torchvision==0.20.0.dev20240726 \
60 --index-url https://download.pytorch.org/whl/nightly/rocm6.1;; \
61 *) ;; esac
62
docs/source/getting_started/amd-installation.rst
+1 -1
@@ -117,7 +117,7 @@ Alternatively, wheels intended for vLLM use can be accessed under the releases.
117
118 $ # Install PyTorch
119 $ pip uninstall torch -y
120 - $ pip install --no-cache-dir --pre torch==2.5.0.dev20240710 --index-url https://download.pytorch.org/whl/nightly/rocm6.1
120 + $ pip install --no-cache-dir --pre torch==2.5.0.dev20240726 --index-url https://download.pytorch.org/whl/nightly/rocm6.1
121
122 $ # Build & install AMD SMI
123 $ pip install /opt/rocm/share/amd_smi