William Lin 57b7be0e1c [Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace (#6971)		2024-08-09 05:42:45 +00:00
..
ops	[Kernel][RFC] Refactor the punica kernel based on Triton (#5036)	2024-07-31 17:12:24 -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] Support dynamically loading Lora adapter from HuggingFace (#6234)	2024-07-22 15:42:40 -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