Sunny-bot1 04035e4ebf support w4afp8 two stage (#5608)

2025-12-22 15:13:05 +08:00

..

graph_optimization

[Others] add assert and only count the actual load in cuda_graph (#5445)

2025-12-10 11:22:54 +08:00

guided_decoding

…

layers

support w4afp8 two stage (#5608)

2025-12-22 15:13:05 +08:00

logits_processor

…

model_loader

…

models

[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

2025-12-18 02:14:25 -08:00

ops

[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

2025-12-18 02:14:25 -08:00

__init__.py

…

forward_meta.py

[Intel HPU] enable tensor_wise_fp8 (#5324)

2025-12-17 16:45:03 +08:00

load_weight_utils.py

remove fastsafetensors (#5371)

2025-12-04 19:22:04 +08:00

pre_and_post_process.py

[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

2025-12-18 02:14:25 -08:00

utils.py

[RL]Support loading weights via the load_weights function for RL (#5549)

2025-12-18 02:27:05 -08:00

xpu_pre_and_post_process.py

…