SangBin ChoandGitHub ff7ec82c4d [Core] Optimize SPMD architecture with delta + serialization optimization (#7109)

2024-08-18 17:57:20 -07:00

..

ops

[Kernel] register punica functions as torch ops (#7591)

2024-08-16 13:59:38 -07:00

__init__.py

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

fully_sharded_layers.py

[Kernel][RFC] Refactor the punica kernel based on Triton (#5036)

2024-07-31 17:12:24 -07:00

layers.py

[Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace (#6971)

2024-08-09 05:42:45 +00:00

lora.py

[Model] Add base class for LoRA-supported models (#5018)

2024-06-27 16:03:04 +08:00

models.py

[Bugfix] Fix LoRA with PP (#7292)

2024-08-08 00:02:27 -07:00

punica.py

[Kernel][RFC] Refactor the punica kernel based on Triton (#5036)

2024-07-31 17:12:24 -07:00

request.py

[Core] Optimize SPMD architecture with delta + serialization optimization (#7109)

2024-08-18 17:57:20 -07:00

utils.py

[LoRA] ReplicatedLinear support LoRA (#7081)

2024-08-02 22:40:19 -07:00

worker_manager.py

[Core] Support dynamically loading Lora adapter from HuggingFace (#6234)

2024-07-22 15:42:40 -07:00