Divakar VermaandAndreas Karatzas dbf1a044ea [Bugfix] Fix ColQwen3.5 pooler projector initialization (#54847) ...

Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

2026-09-02 10:35:43 +08:00

..

determinism

[Perf] Autotune batch invariance triton kernel in blackwell, 33.6% E2E latency reduction (#53649)

2026-08-25 15:06:01 -04:00

hw_agnostic

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00

kernels

[Kimi-K3][Perf] Prefetch ll_bf16 router weights for M=1 (#53524)

2026-09-01 21:40:19 +00:00

layers

[Bugfix] Restore weight_dtype in QuarkW8A8Fp8MoEMethod to fix GPT-OSS FP8 MoE weight loading (#54824)

2026-09-01 16:08:11 -05:00

model_loader

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

models

[Bugfix] Fix ColQwen3.5 pooler projector initialization (#54847)

2026-09-02 10:35:43 +08:00

offloader

[Offloader] Offload submodules that make_layers never reaches (#53120)

2026-08-26 18:37:00 +08:00

warmup

[Qwen3.8-Flash-Next] Separate prefill and decode paths for QSA indexer (#54513)

2026-09-02 09:08:10 +08:00

__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