Matej SirovatkaandJee Jee Li 3ac9525507 [Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074) ...

Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>

2026-08-12 14:06:53 +08:00

..

kernels

[XPU] [Linear] enable torch linear backend for blockwise gemm on xpu (#50826)

2026-08-11 16:43:33 +08:00

layers

[Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074)

2026-08-12 14:06:53 +08:00

model_loader

[Bugfix] Avoid repeated layerwise reload warning scans (#49505)

2026-08-12 13:53:50 +08:00

models

[Perf] Avoid more GPU<->CPU syncs on the model execution path (#51738)

2026-08-11 19:30:34 -07:00

offloader

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

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

warmup

[2/N][Feat][Perf] Add new warmup infrastructure for JITs. Add predicate filtering for JIT warmup, and migrate Inkling FA4 (#49315)

2026-08-11 07:46:07 -04:00

__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

[Weight processing] Copy over new_data attributes in replace_parameter (#49601)

2026-08-06 13:03:37 -04:00