Li, Jiang b68408043d [Bugfix][CPU] Add per-tensor FP8 W8A16 kernel to fix Ministral crash on CPU (#56985) ...

Signed-off-by: jiang1.li <jiang1.li@intel.com>

2026-09-16 15:49:17 +08:00

..

general

[Cleanup] Remove vestigial tpu_input_batch.py (#56898)

2026-09-14 21:29:15 -07:00

spec_decode

[Spec][V2] Support MTP speculative decoding under pipeline parallelism (#46994)

2026-09-11 17:55:21 +00:00

__init__.py

[V1] Implement Cascade Attention (#11635)

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

test_cpu_linear_attn_chunked_prefix.py

[CI] Shard CPU jobs above the 24h P90 threshold (#54751)

2026-09-02 02:16:05 -07:00

test_cpu_spec_decode.py

[Bugfix][CPU] Add per-tensor FP8 W8A16 kernel to fix Ministral crash on CPU (#56985)

2026-09-16 15:49:17 +08:00

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

[Mamba] Add FlashInfer ReplaySSM backend (#52506)

2026-09-01 10:26:43 -04:00