Liangsheng Yin 7395ee833e [CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944)

2026-08-07 01:22:22 -07:00

..

breakable

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944)

2026-08-07 01:22:22 -07:00

full_prefill

[FullCG] Support chunked cached-prefix prefill (#30825)

2026-07-28 11:20:25 -07:00

piecewise

[Fix] Resolve VLM test image placeholders from the model's own chat template (#33509)

2026-08-04 02:01:39 -07:00

test_cuda_piecewise_backend.py

fix: fix vlm cuda graph shape stability (#30868)

2026-07-19 22:35:51 +08:00