MHYangAMDandMHYangAMD ab12aab127 [Bugfix] [ROCm] [DSV4] Fix AITER MXFP4 MoE weight loading and shuffle… (#42595) ...

Co-authored-by: MHYangAMD <MHYangAMD@users.noreply.github.com>

2026-05-29 04:08:33 -07:00

..

kernels

[Kernel][ROCm] Native W4A16 kernel for AMD RDNA3 (gfx1100) — fp16 + bf16 (#41394)

2026-05-29 11:04:40 +00:00

layers

[Bugfix] [ROCm] [DSV4] Fix AITER MXFP4 MoE weight loading and shuffle… (#42595)

2026-05-29 04:08:33 -07:00

model_loader

Add Cosmos3 Reasoner model (#43356)

2026-05-28 09:43:55 -07:00

models

[Bugfix] Fix Step3 pipeline parallel KeyError for residual tensor (#37622)

2026-05-29 03:04:02 -07:00

offloader

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

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

warmup

[CI failure] Temporarily disable using persistent cache for flashinfer autotune (#43119)

2026-05-19 11:44:32 -07:00

__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

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

utils.py

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

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