qizixi e2db0222e9 [Perf][Attention] Pin MLA chunked-context metadata tensors so H2D copies are truly non-blocking (#45074) ...

Signed-off-by: zixi-qi <zixi@inferact.ai>

2026-06-10 15:56:49 -07:00

..

kernels

[bugfix] skip conch kernel for g_idx reordering (#45072)

2026-06-10 23:04:19 +08:00

layers

[Perf][Attention] Pin MLA chunked-context metadata tensors so H2D copies are truly non-blocking (#45074)

2026-06-10 15:56:49 -07:00

model_loader

[Bugfix] Fix Llama4 weight loading (#45047)

2026-06-10 13:40:45 -04:00

models

feat(qwen3-asr): support prompt parameter in v1/audio/transcriptions (#35415)

2026-06-10 19:54:59 +00:00

offloader

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

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

warmup

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

__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