Jiang-Jia-Jun c56c99837a Revert "[BugFix] num_seqs (#3291)" (#3316) ...

This reverts commit e0aeac58e1.

2025-08-11 16:16:51 +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

[V1 Loader] Support DeepSeekV3(bf16) (#3294)

2025-08-11 13:39:28 +08:00

model_loader

[feat]add fast_weights_iterator (#3258)

2025-08-07 22:36:46 +08:00

models

Revert "[BugFix] num_seqs (#3291)" (#3316)

2025-08-11 16:16:51 +08:00

ops

[Iluvatar GPU] Optimze attention and moe performance (#3234)

2025-08-08 10:51:24 +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

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

2025-08-08 15:55:47 +08:00

pre_and_post_process.py

enhance eos_tokens (#3274)

2025-08-11 14:47:52 +08:00