Jee Jee Li a4cf256159

[Bugfix] Fix QKVParallelLinearWithShardedLora bias bug (#10844) ...

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

2024-12-03 12:10:29 +08:00

..

ops

[Kernel] Register punica ops directly (#10522)

2024-11-21 09:18:11 -08:00

__init__.py

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

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

fully_sharded_layers.py

[Bugfix] Fix QKVParallelLinearWithShardedLora bias bug (#10844)

2024-12-03 12:10:29 +08:00

layers.py

[Misc][LoRA] Move the implementation of lora bias to punica.py (#10829)

2024-12-02 17:53:36 +00:00

lora.py

[LoRA] Adds support for bias in LoRA (#5733)

2024-11-12 11:08:40 -08:00

models.py

[LoRA] Adds support for bias in LoRA (#5733)

2024-11-12 11:08:40 -08:00

punica.py

[Misc][LoRA] Move the implementation of lora bias to punica.py (#10829)

2024-12-02 17:53:36 +00:00

request.py

[Core] Support Lora lineage and base model metadata management (#6315)

2024-09-20 06:20:56 +00:00

utils.py

[LoRA] Adds support for bias in LoRA (#5733)

2024-11-12 11:08:40 -08:00

worker_manager.py

[Misc][LoRA] Replace hardcoded cuda device with configurable argument (#10223)

2024-11-12 11:10:15 +08:00