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 8, 08:45 UTC
[ROCm][CI] Pin TorchCodec to v0.10.0 for ROCm compatibility (#34447)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Feb 12, 2026 at 12:47 UTC
4c078fa546016eacab87f833ff625463421f7d29
1 file changed
+2
-1
tools/install_torchcodec_rocm.sh
+2
-1
@@ -7,7 +7,8 @@
7
set -e
8
9
TORCHCODEC_REPO="${TORCHCODEC_REPO:-https://github.com/pytorch/torchcodec.git}"
10
-TORCHCODEC_BRANCH="${TORCHCODEC_BRANCH:-main}"
10
+# Pin to a specific release for reproducibility; update as needed.
11
+TORCHCODEC_BRANCH="${TORCHCODEC_BRANCH:-v0.10.0}"
12
13
echo "=== TorchCodec Installation Script ==="
14