yzwu fbdd6b0663 [Iluvatar GPU] Optimze attention and moe performance (#3234)

2025-08-08 10:51:24 +08:00

..

ce/server

[stop_seq] fix out-bound value for stop sequence (#3216)

2025-08-07 15:40:21 +08:00

ci_use

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

2025-08-08 10:51:24 +08:00

entrypoints/openai

[Bugfix] Fix uninitialized decoded_token and add corresponding unit test. (#3195)

2025-08-04 19:23:58 +08:00

graph_optimization

[Executor]Update graph test case and delete test_attention (#3257)

2025-08-07 14:05:15 +08:00

layers

[Executor]Update graph test case and delete test_attention (#3257)

2025-08-07 14:05:15 +08:00

operators

[New Feature] Support W4Afp8 MoE GroupGemm (#3171)

2025-08-06 10:34:05 +08:00

plugins

[plugin] Custom model_runner/model support (#3186)

2025-08-04 18:52:39 -07:00

utils

[fix] multi source download (#3259)

2025-08-07 19:30:39 +08:00