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 16, 22:00 UTC
[ CI ] Temporarily Disable Large LM-Eval Tests (#6005)
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic>
Robert Shaw committed
Jun 30, 2024 at 14:56 UTC
deacb7ec44cd816648eb856959472f1fef01f883
1 file changed
-9
.buildkite/test-pipeline.yaml
-9
@@ -198,15 +198,6 @@ steps:
198
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
199
- bash ./run-tests.sh -c configs/models-small.txt -t 1
200
201
-- label: LM Eval Large Models
202
- gpu: a100
203
- num_gpus: 4
204
- working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
205
- commands:
206
- - pip install lm-eval
207
- - export VLLM_WORKER_MULTIPROC_METHOD=spawn
208
- - bash ./run-tests.sh -c configs/models-large.txt -t 4
209
-
201
- label: Documentation Build
202
working_dir: "/vllm-workspace/test_docs/docs"
203
no_gpu: True