Hanjun Cho f600d5192e [Bugfix] Fix score layer quantization for sequence classification models - Qwen3 (VL) Reranker (#35849) ...

Signed-off-by: Hanjun Cho <gkswns0531@gmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

2026-03-04 20:57:20 -08:00

..

kernels

[CPU][Feat] Enable KleidiAI INT8_W4A8 for all input dtypes (#34890)

2026-02-26 05:00:10 +00:00

layers

[Misc] Support OOT linear method registering (#35981)

2026-03-04 22:25:56 +00:00

model_loader

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

models

[Bugfix] Fix score layer quantization for sequence classification models - Qwen3 (VL) Reranker (#35849)

2026-03-04 20:57:20 -08:00

offloader

[UX] Remove NoOpOffloader log (#35678)

2026-03-04 12:13:40 -08:00

warmup

[MoE Refactor] Create MK for TRTLLM Kernels (#32564)

2026-03-03 10:39:50 -08:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

[Model Bash][DSR1] Add selective dynamic shape marking for CustomOp (#34900)

2026-02-21 19:28:01 -05:00

parameter.py

[QeRL] Layerwise Reloading (#32133)

2026-01-30 08:50:05 -07:00

utils.py

[BugFix] Fix EPLB fail for MoeFP4 model with Marlin backend (#33262)

2026-01-29 16:52:11 +08:00