3 people 523d74e2ac [Bugfix][LoRA] Fix garbage/NaN lora_expand output on SM90 with fp32 i… (#61906) ...

Signed-off-by: BeichenHuang <polarishuang0.0@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>

2026-10-16 19:42:30 -04:00

..

layers

[Bugfix][LoRA] Slice expert LoRA by the unpadded per-rank size under TP (#61235)

2026-10-13 14:25:16 +08:00

ops

[Bugfix][LoRA] Fix garbage/NaN lora_expand output on SM90 with fp32 i… (#61906)

2026-10-16 19:42:30 -04:00

punica_wrapper

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

__init__.py

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

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

lora_model.py

[Bugfix][LoRA] Apply PEFT rank_pattern / alpha_pattern scaling per module (#59801)

2026-10-12 21:49:30 +08:00

lora_weights.py

[Bugfix][LoRA] Apply PEFT rank_pattern / alpha_pattern scaling per module (#59801)

2026-10-12 21:49:30 +08:00

model_manager.py

[Refactor] Remove dead code multiple places (#60120)

2026-10-10 15:41:10 +00:00

peft_helper.py

[Bugfix][LoRA] Apply PEFT rank_pattern / alpha_pattern scaling per module (#59801)

2026-10-12 21:49:30 +08:00

request.py

[LoRA] Remove tensorizer (#60024)

2026-10-05 07:01:56 -07:00

resolver.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

utils.py

[Bugfix][LoRA] Reject PEFT adapter features vLLM does not implement (#60225)

2026-10-09 16:39:58 +04:00

worker_manager.py

[Bugfix][LoRA] Validate incompatible MoE adapter formats (#59924)

2026-10-09 09:49:13 +08:00