Thien Tran 6ec92bcbc8 [Kimi-K3] Merge MLA gate into QKV-A projection (#54015) ...

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>

2026-08-27 17:47:18 -07:00

..

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

[kernel] Integrate FlashInfer BF16 CuTeDSL Low Latency GEMM (#50572)

2026-08-27 22:29:12 +00:00

layers

[Kimi-K3] Merge MLA gate into QKV-A projection (#54015)

2026-08-27 17:47:18 -07:00

model_loader

Add routed expert loading for gpt-oss (#52209)

2026-08-23 17:59:08 +08:00

models

fix(config): guard LlamaBidirectionalConfig against missing hf_config.pooling (#50536)

2026-08-27 18:56:07 +08:00

offloader

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

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

warmup

[kernel] Integrate FlashInfer BF16 CuTeDSL Low Latency GEMM (#50572)

2026-08-27 22:29:12 +00:00

__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