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 11, 23:45 UTC
[ROCm][CI] Add jiwer dependency for testing (#30081)
Signed-off-by: charlifu <charlifu@amd.com>
Charlie Fu committed
Dec 4, 2025 at 21:34 UTC
7c9b2c8f8132e47fa9b04c0ae9a49872e0172f5f
1 file changed
+1
requirements/rocm-test.txt
+1
@@ -58,6 +58,7 @@ schemathesis==3.39.15
58
59
# Evaluation and benchmarking
60
lm-eval[api] @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d
61
+jiwer==4.0.0
62
63
# Required for multiprocessed tests that use spawn method, Datasets and Evaluate Test
64
multiprocess==0.70.16