Lifu Huang 9241f4fd20 Move cached kernel to srt.utils (#10776)

2025-09-22 23:00:36 -07:00

..

backend

[3/4] Speed up CSGMV backend perf by 10% through dynamic chunking + kernel optimization (#10592)

2025-09-20 22:47:48 -07:00

triton_ops

Move cached kernel to srt.utils (#10776)

2025-09-22 23:00:36 -07:00

layers.py

[1/2] Refactor LoRA to support backend-specific batch preprocessing. (#10251)

2025-09-10 09:58:37 -07:00

lora_config.py

[Fix] Fix bugs and refactor codes in lora for better scalability. (#3652)

2025-02-20 11:51:57 -08:00

lora_manager.py

[3/4] Speed up CSGMV backend perf by 10% through dynamic chunking + kernel optimization (#10592)

2025-09-20 22:47:48 -07:00

lora_registry.py

Support pinning adapter via server args. (#9249)

2025-08-20 16:25:01 -07:00

lora.py

[2/2] Introduce Chunked-SGMV kernels and corresponding LoRA backend for improved performance (#10286)

2025-09-15 16:04:03 -07:00

mem_pool.py

support Llama4 with non uniformed intermediate size across layers for… (#10047)

2025-09-05 17:28:15 -07:00

utils.py

[3/4] Speed up CSGMV backend perf by 10% through dynamic chunking + kernel optimization (#10592)

2025-09-20 22:47:48 -07:00