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 15, 01:00 UTC
Fix bad lm-eval fork (#21318)
Michael Goin committed
Jul 21, 2025 at 13:47 UTC
005ae9be6c22dfa2c2c5580b50b41e67faee4a87
1 file changed
+1
-1
.buildkite/test-pipeline.yaml
+1
-1
@@ -273,7 +273,7 @@ steps:
273
# VLLM_USE_FLASHINFER_SAMPLER or not on H100.
274
- pytest -v -s v1/e2e
275
# Integration test for streaming correctness (requires special branch).
276
- - pip install -U git+https://github.com/robertgshaw2-neuralmagic/lm-evaluation-harness.git@streaming-api
276
+ - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
277
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
278
279
- label: Examples Test # 25min