danisereb 5b2a9422f0 [BugFix] Fix LoRA Fp8 (#33879) ...

Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>

2026-02-05 17:25:55 +00:00

..

layers

[BugFix] Fix LoRA Fp8 (#33879)

2026-02-05 17:25:55 +00:00

ops

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

punica_wrapper

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

__init__.py

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

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

lora_model.py

[LoRA][Spec Decode] Support LoRA for Nemotron-H MTP models (#32265)

2026-01-27 07:53:26 -08:00

lora_weights.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

model_manager.py

[Refactor] Move profiling methods to MM budget (#33559)

2026-02-02 23:27:00 +08:00

peft_helper.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

request.py

[Feat] allow inplace loading lora (#31326)

2026-01-20 10:15:20 +08:00

resolver.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

utils.py

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

worker_manager.py

[LoRA][Spec Decode] Support LoRA for Nemotron-H MTP models (#32265)

2026-01-27 07:53:26 -08:00