Ethan (Yusheng) Su 7f6f1a3ab1 [LoRA][II] Add fused MOE LoRA Triton kernel and tests (#19711)

2026-03-18 19:58:14 -07:00

..

backend

Enable embedding lookup/lora_a logic for chunked backend (#17692)

2026-03-16 11:37:58 -07:00

torch_ops

[NPU] make torch_native lora backend a little bit faster (#17228)

2026-03-07 20:14:46 +03:00

triton_ops

[LoRA][II] Add fused MOE LoRA Triton kernel and tests (#19711)

2026-03-18 19:58:14 -07:00

eviction_policy.py

Feature/Fix multi lora scheduler blocking issue and evict LoRA None lastly (#14795)

2025-12-12 17:13:05 -08:00

layers.py

Support TP for lora lm_head layer (#18511)

2026-03-18 13:48:03 -07:00

lora_config.py

Update LoRA Weights via Tensor (#16226)

2026-01-10 17:36:43 +08:00

lora_manager.py

[Fix] Add lora tied lm head support (for Qwen2.5, Gemma, etc model need) (#18634)

2026-02-19 00:34:51 +08:00

lora_overlap_loader.py

[Feature] overlap LoRA weight loading with compute (#15512)

2026-01-19 10:43:17 +08:00

lora_registry.py

allow loras to be implicitly evicted and loaded based on max_loaded_loras (#11526)

2025-11-20 13:34:32 -08:00

lora.py

[Fix] Add lora tied lm head support (for Qwen2.5, Gemma, etc model need) (#18634)

2026-02-19 00:34:51 +08:00

mem_pool.py

Support TP for lora lm_head layer (#18511)

2026-03-18 13:48:03 -07:00

utils.py

Support TP for lora lm_head layer (#18511)

2026-03-18 13:48:03 -07:00