Artus Krohn-Grimberghe eadb4e868b [Bugfix] Avoid duplicate k-proj weight emission in helper (#34142) ...

Signed-off-by: Artus KG <artuskg@gmail.com>

2026-02-09 19:17:44 +00:00

..

layers

[Bugfix] Fix shared expert input for latent MoE in EP+DP (Nemotron-H) (#34087)

2026-02-09 16:44:18 +00:00

model_loader

[BugFix] Fix fastsafetensors TP all procs using all GPUs (#34070)

2026-02-09 15:15:46 +08:00

models

[Bugfix] Avoid duplicate k-proj weight emission in helper (#34142)

2026-02-09 19:17:44 +00:00

warmup

[Kernel] Add KernelConfig flag to enable/disable FlashInfer autotune (#34006)

2026-02-07 05:24:44 -08:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

[torch.compile] Compile CustomOp.forward_native for SiluAndMul and QuantFP8 to avoid raw torch ops inside opaque custom ops (#32806)

2026-01-22 19:52:26 -08:00

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