Wei ZhaoandOpenAI Codex 8c87c333b8 [Perf] Fix TRTLLM ragged prefill perf regression (#55499) ...

Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-09-09 20:38:20 +00:00

..

determinism

[Docs] Add missing return annotations flagged by griffe (#54980)

2026-09-02 09:56:07 -07:00

hw_agnostic

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00

kernels

[Kernel] Add NVFP4 support to the torch linear backend (#53319)

2026-09-08 20:30:05 -04:00

layers

[Perf] Fix TRTLLM ragged prefill perf regression (#55499)

2026-09-09 20:38:20 +00:00

model_loader

[Qwen4Exp] Support UVA PLE-offload and Engram tensor parallelism (#54371)

2026-09-09 07:32:34 -07:00

models

[Bugfix] Make mm_device_do_normalize encoder-cudagraph safe (#55370)

2026-09-10 01:43:22 +08:00

offloader

[Core] Enhance cpu<->gpu sync checking to include paged async copies (#53491)

2026-09-08 17:26:21 -07:00

warmup

[Perf] Improve BF16x3 router GEMM accuracy and make it default on sm100 (#55899)

2026-09-09 07:33:12 -07:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

[Bugfix] Reject contradictory custom-op directives (#49134)

2026-07-26 08:42:14 -04:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Fast Start (#54921)

2026-09-04 06:32:06 -07:00