4 people 3723a1ea96 [Bugfix][Transformers backend] Fix CUDA graph capture for dynamic-rope models (#58064) ...

Signed-off-by: YongfengX <erkang040804@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>

2026-10-14 05:56:54 -07:00

..

determinism

[Feature] Support batch invariance on ROCm (#52231)

2026-10-12 10:53:26 -05:00

hw_agnostic

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

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

kernels

[XPU] [Linear] [MXFP8] enable torch as mxfp8 linear backend (#51933)

2026-10-14 00:48:38 -07:00

layers

[ROCm] Disable AITER FP8/FP4 BMM for MLA by default (#53123)

2026-10-14 10:46:02 +00:00

model_loader

[Bugfix][RL] Load attention sinks through weight_loader for layerwise reload (#57797)

2026-10-14 10:17:58 +00:00

models

[Bugfix][Transformers backend] Fix CUDA graph capture for dynamic-rope models (#58064)

2026-10-14 05:56:54 -07:00

offloader

[MRV2] Release weight offloader on shutdown (#57834)

2026-09-22 15:01:20 -04:00

warmup

[Perf] Warm up DeepGEMM MegaMoE kernels before serving (#60468)

2026-10-13 20:17:48 +08:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

parameter.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

utils.py

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

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