youkaichao 614aa51203 [misc][cuda] use nvml to avoid accidentally cuda initialization (#6007)		2024-06-30 20:07:34 -07:00
..
__init__.py	[Experimental] Add multi-LoRA support (#1804)	2024-01-23 15:26:37 -08:00
fully_sharded_layers.py	[Bugfix] Add fully sharded layer for QKVParallelLinearWithLora (#5665)	2024-06-21 04:46:28 +00:00
layers.py	[Model] Add Gemma 2 (#5908)	2024-06-27 13:33:56 -07:00
lora.py	[Model] Add base class for LoRA-supported models (#5018)	2024-06-27 16:03:04 +08:00
models.py	[Lora] Use safetensor keys instead of adapter_config.json to find unexpected modules. (#5909)	2024-06-30 17:11:15 +00:00
punica.py	[misc][cuda] use nvml to avoid accidentally cuda initialization (#6007)	2024-06-30 20:07:34 -07:00
request.py	[Lora] Support long context lora (#4787)	2024-05-18 16:05:23 +09:00
utils.py	[Bugfix] Add fully sharded layer for QKVParallelLinearWithLora (#5665)	2024-06-21 04:46:28 +00:00
worker_manager.py	[LoRA] Add support for pinning lora adapters in the LRU cache (#5603)	2024-06-21 15:42:46 -07:00