amirkl94 8b2b566ea7 Feature: Enable Flashinfer non-gated MoE bf16 (#43853) ...

Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>

2026-06-17 14:32:49 +00:00

..

kernels

[Bugfix][ROCm] Fix FP8 per-tensor scale rank mismatch causing Inductor assertion failure (#44912)

2026-06-16 20:17:42 -07:00

layers

Feature: Enable Flashinfer non-gated MoE bf16 (#43853)

2026-06-17 14:32:49 +00:00

model_loader

[Core] Use fastsafetensors ParallelLoader for weight loading (#40183)

2026-06-15 22:32:05 -07:00

models

[MM][Perf][CG] Support ViT full CUDA graph for Kimi-VL (#41992)

2026-06-17 12:14:01 +00:00

offloader

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

warmup

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

Speed up docs build (#44635)

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

utils.py

[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)

2026-05-06 10:32:26 +00:00