chenjian d2f6c3b998 [Bug fix] Fix bug for seq_len_encoder is 1 (#3467)

2025-08-19 15:21:32 +08:00

..

graph_optimization

update flake8 version to support pre-commit in python3.12 (#3000)

2025-07-24 01:43:31 -07:00

guided_decoding

Unify server-side and model-side Config (Part3) (#3047)

2025-07-29 17:07:44 +08:00

layers

[Bug fix] Fix bug for seq_len_encoder is 1 (#3467)

2025-08-19 15:21:32 +08:00

model_loader

【Feature】add fd plugins && rm model_classes (#3123)

2025-08-03 19:53:20 -07:00

models

【Feature】add fd plugins && rm model_classes (#3123)

2025-08-03 19:53:20 -07:00

ops

moe preprocess op support 160 experts and fused_moe triton kernel name add K (#3121)

2025-08-01 10:46:20 +08:00

__init__.py

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

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

forward_meta.py

[Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989)

2025-07-31 00:09:31 +08:00

load_weight_utils.py

fix load_pre_sharded_checkpoint (#3152)

2025-08-04 10:44:20 +08:00

pre_and_post_process.py

[Feature] Support batched tokens for EP (#3415)

2025-08-18 11:43:36 +08:00