Add vllm bench [latency, throughput] CLI commands (#16508)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-04-15 00:10:35 -06:00
committed by GitHub
parent bc5dd4f669
commit b4fe16c75b
11 changed files with 1771 additions and 2 deletions

View File

@@ -341,6 +341,13 @@ steps:
commands:
- bash scripts/run-benchmarks.sh
- label: Benchmarks CLI Test # 10min
source_file_dependencies:
- vllm/
- tests/benchmarks/
commands:
- pytest -v -s benchmarks/
- label: Quantization Test # 33min
source_file_dependencies:
- csrc/