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, 17:45 UTC
[ROCm][CI] Pinning lm-eval version to resolve multi-modal small eval bug (#34038)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Feb 7, 2026 at 00:21 UTC
c490d8cc7389860c1c6f9ae4181c023c7350738f
1 file changed
+1
-1
requirements/rocm-test.txt
+1
-1
@@ -58,7 +58,7 @@ schemathesis==3.39.15
58
# OpenAI schema test
59
60
# Evaluation and benchmarking
61
-lm-eval[api]>=0.4.9.2
61
+lm-eval[api]==0.4.9.2
62
jiwer==4.0.0
63
64
# Required for multiprocessed tests that use spawn method, Datasets and Evaluate Test