Gabriel WuandYongye Zhu 2e35c529b8 [Bugfix][Quantization] Fix MXFP4 conversion for FlashInfer CUTLASS (#51038) ...

Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

2026-08-05 23:19:22 -07:00

..

kernels

[XPU] Support MXFP8 linear weights for INC DeepSeek V4 model (#48476)

2026-08-06 13:17:48 +08:00

layers

[Bugfix][Quantization] Fix MXFP4 conversion for FlashInfer CUTLASS (#51038)

2026-08-05 23:19:22 -07:00

model_loader

[Bugfix][MoE] Filter packed expert weights during EP loading (#49558)

2026-08-04 16:32:03 +00:00

models

[MM][CG] Support ViT full CUDA graph for Ernie-4.5-VL image inference (#45254)

2026-08-06 05:04:19 +00:00

offloader

Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)

2026-07-06 14:18:33 +01:00

warmup

[UX] Reduce startup log noise (#50590)

2026-07-31 13:04:34 -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

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00