Misha Goin a34f2ab70a [Test] Add focused hybrid MTP prefix-cache regressions (#53189) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2026-08-21 17:05:39 -07:00

..

general

[Bugfix][Core] Reserve the KV null block when validating max_model_len (#47272)

2026-08-20 02:49:23 +00:00

spec_decode

[Bugfix] test_batch_inference_correctness now uses batch invariance (#48040)

2026-08-21 09:06:59 -07:00

__init__.py

[V1] Implement Cascade Attention (#11635)

2025-01-01 21:56:46 +09:00

test_cpu_linear_attn_chunked_prefix.py

[CPU] Enable chunked prefill and prefix caching for qwen3.5 (#46202)

2026-06-25 03:49:21 +00:00

test_hybrid_chunked_prefill.py

[Test] Add focused hybrid MTP prefix-cache regressions (#53189)

2026-08-21 17:05:39 -07:00

test_replayssm_decode.py

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00