fxyfxy777 36547cfdb3 [Feature] FD_USE_PHI_FP8_QUANT (#6320) ...

* add ut

* add use_fd_quant env

* rm mask_per_token_quant

* add make ops list

* USE_FD_FP8_QUANT -> FD_USE_PHI_FP8_QUANT 默认是true

* modify comments

* use bool type

* Add function declaration

2026-02-03 22:33:03 -08:00

..

graph_optimization

[Graph Optimization] Support CUDAGraph for P/PD mixed Batch using SOT subgraph spliting mode (#6196)

2026-01-29 16:29:54 +08:00

guided_decoding

[Feature] Guided Decoding add LLguidance backend (#5124)

2025-12-03 20:23:57 +08:00

layers

[Feature] FD_USE_PHI_FP8_QUANT (#6320)

2026-02-03 22:33:03 -08:00

logits_processor

[Feature] support logits processors (#4515)

2025-10-29 00:08:53 +08:00

model_loader

[Loader] support dummy load weight (#6169)

2026-01-26 13:58:53 +08:00

models

Revert "[RL] Support GLM MTP RL Model (#6223)" (#6301)

2026-02-02 14:08:13 +08:00

ops

[build] support build sm 80,86,89,90 to one whl package (#6173)

2026-01-26 11:30:02 +08:00

__init__.py

…

entropy_utils.py

[Bugfix] Fix entropy calculation bugs (#5941)

2026-01-08 20:57:35 +08:00

forward_meta.py

[Graph Optimization] Support CUDAGraph for P/PD mixed Batch using SOT subgraph spliting mode (#6196)

2026-01-29 16:29:54 +08:00

load_weight_utils.py

[Intel HPU] enable MoE EP for hpu (#5855)

2026-01-15 13:08:00 +08:00

pre_and_post_process.py

[Model Runner] Support overlap schedule (#6259)

2026-02-04 10:49:44 +08:00

utils.py

[Feature] Support NVFP4 MoE on SM100 (#6003)

2026-01-29 14:16:07 +08:00

xpu_pre_and_post_process.py

[Feature]Support reorder ids to split prefill and decodes (#5779)

2026-02-03 00:28:02 -08:00