WANG HAO bd8c999335 Further optimize multi-lora inference,LoRA-enabled performance achieves 80%+ of non-LoRA performance (#190) ...

* optimize lora inference

Signed-off-by: wanghao <wanghao@example.com>

* further optimize multi-lora inference,LoRA-enabled performance achieves 80%+ of non-LoRA performance

Signed-off-by: wanghao <wanghao@example.com>

---------

Signed-off-by: wanghao <wanghao@example.com>
Co-authored-by: wanghao <wanghao@example.com>

2026-02-11 12:04:14 +08:00

..

ops

Further optimize multi-lora inference,LoRA-enabled performance achieves 80%+ of non-LoRA performance (#190)

2026-02-11 12:04:14 +08:00

punica_wrapper

Further optimize multi-lora inference,LoRA-enabled performance achieves 80%+ of non-LoRA performance (#190)

2026-02-11 12:04:14 +08:00

__init__.py

[Feature] totaly support multi-lora support,latest xspeedgate needed (#133)

2026-01-20 21:27:02 +08:00