3 people af2a582d5c [Bugfix][Spec Decode] Qualify Transformers backend attention layer names with the model prefix (#59293) ...

Signed-off-by: Farhad Al-Amin <99006654+Legend-2727@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-10-02 11:21:20 +01:00

..

general

[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)

2026-10-01 23:04:21 -07:00

spec_decode

[Bugfix][Spec Decode] Qualify Transformers backend attention layer names with the model prefix (#59293)

2026-10-02 11:21:20 +01:00

__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

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_replayssm_decode.py

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00