Liangsheng Yin 909123ddb8 [misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)

2026-06-28 18:38:28 -07:00

..

__init__.py

Add the KV-canary core: data layer, MHA KV-pool patcher, and per-forward runner (#26808)

2026-05-31 09:54:24 +08:00

consts.py

[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)

2026-06-28 18:38:28 -07:00

e2e_base.py

Add kv_canary PP self-test fixture and SWA divergence coverage (#27410)

2026-06-06 09:06:19 +08:00

fixtures.py

Add periodic KV-canary stats logging and kernel-run-counter health check (#26821)

2026-05-31 10:00:19 +08:00

mode_config.py

Add KV-canary SWA + DeepSeek-V4 pool support (#26810)

2026-05-31 09:55:34 +08:00

pd_fixture.py

Fix flaky test_self_e2e_pd_perturb (#27426)

2026-06-06 19:31:08 +08:00

pp_fixture.py

Add kv_canary PP self-test fixture and SWA divergence coverage (#27410)

2026-06-06 09:06:19 +08:00

runner_test_base.py

Add periodic KV-canary stats logging and kernel-run-counter health check (#26821)

2026-05-31 10:00:19 +08:00

utils.py

Add kv_canary PP self-test fixture and SWA divergence coverage (#27410)

2026-06-06 09:06:19 +08:00

violation_assert_mixin.py

Add the KV-canary perturb framework for fault-injection self-tests (#26816)

2026-05-31 09:58:14 +08:00

violation_log_utils.py

Add the KV-canary core: data layer, MHA KV-pool patcher, and per-forward runner (#26808)

2026-05-31 09:54:24 +08:00