biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling (#38045)

Browse Source 
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
This commit is contained in:
Giancarlo Delfin
2026-03-26 13:38:12 -07:00
committed by GitHub
parent 0904b6550d
commit c32e97602d
7 changed files with 240 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/test_areas/model_runner_v2.yaml
View File

@@ -101,9 +101,11 @@ steps:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/v1/spec_decode/test_max_len.py
- tests/v1/spec_decode/test_synthetic_rejection_sampler_utils.py
- tests/v1/e2e/spec_decode/test_spec_decode.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pytest -v -s v1/spec_decode/test_max_len.py -k "eagle or mtp"
- pytest -v -s v1/spec_decode/test_synthetic_rejection_sampler_utils.py
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle or mtp"