3 people f2376cdc4d [Fast Start] Preload the FlashInfer autotune table on the weight cache daemon (#60085) ...

Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>

2026-10-10 15:48:06 +00:00

..

__init__.py

[Fast Start] Cache the MTP draft model in a separate daemon group (#57312)

2026-09-22 03:13:38 +00:00

daemon.py

[Fast Start] Preload the FlashInfer autotune table on the weight cache daemon (#60085)

2026-10-10 15:48:06 +00:00

ipc_loader.py

[Fast Start] Charge daemon-held weights against gpu_memory_utilization (#57298)

2026-09-29 17:58:35 +00:00

protocol.py

[quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)

2026-10-07 22:01:09 +00:00

utils.py

[Fast Start] Preload the FlashInfer autotune table on the weight cache daemon (#60085)

2026-10-10 15:48:06 +00:00