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 9, 05:00 UTC
[ROCm][CI] Update huggingface-hub pin (#33492)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Jan 31, 2026 at 20:51 UTC
0fb3157267127a69667f5c9b92d030c0de10614a
1 file changed
+2
requirements/rocm-test.txt
+2
@@ -94,3 +94,5 @@ timm==1.0.17
94
albumentations==1.4.6
95
# Pin transformers version
96
transformers==4.57.3
97
+# Pin HF Hub version
98
+huggingface-hub==0.36.0