chen ad202272ed 【Infer】Improve the performance block_wise_fp8 of triton_moe_backend (#2942)

2025-07-23 13:02:50 +08:00

..

graph_optimization

[SOT] Add sot warmup (NVIDIA GPU Only) (#2929)

2025-07-22 21:36:14 +08:00

guided_decoding

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

layers

【Infer】Improve the performance block_wise_fp8 of triton_moe_backend (#2942)

2025-07-23 13:02:50 +08:00

models

[SOT] Mark dynamic dims by type annotations (#2771)

2025-07-22 00:23:52 -07:00

ops

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

forward_meta.py

use dist.all_reduce(min) to sync num_blocks_local (#2933)

2025-07-21 01:23:36 -07:00

load_weight_utils.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

model_loader.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

pre_and_post_process.py

native top_p_sampling (#2901)

2025-07-22 14:09:59 +08:00