YuBaoku 54f7d9f621 [CI] Sync mm_batch_invariant with paddle.mm update (#6557)

2026-02-28 14:56:42 +08:00

..

graph_optimization

[Speculative Decoding] Support suffix decoding (#6403)

2026-02-26 11:42:05 +08:00

guided_decoding

…

layers

[CI] Sync mm_batch_invariant with paddle.mm update (#6557)

2026-02-28 14:56:42 +08:00

logits_processor

[Feature] Support ThinkingBudget Logits processor to control thinking content length (#6367)

2026-02-25 14:17:09 +08:00

model_loader

[BugFix] Fix model loading error for 300B FP8 EP parallel test case (#6382)

2026-02-10 11:32:57 +08:00

models

add dsv3 mixed deploy as EP16 TP8 (#6525)

2026-02-27 14:08:25 +08:00

ops

[Fix] Use paddle.device.get_device_properties for multi-platform compatibility (#6400)

2026-02-09 19:15:41 +08:00

__init__.py

…

entropy_utils.py

…

forward_meta.py

…

load_weight_utils.py

[loader]supoort wint2 backend (#6139)

2026-02-08 22:42:36 -08:00

pre_and_post_process.py

[OP][Feature] 统一 limit_thinking_content_length CUDA 算子，支持回复长度限制与注入序列 (#6493)

2026-02-25 21:36:50 +08:00

utils.py

[BugFix] Fix model loading error for 300B FP8 EP parallel test case (#6382)

2026-02-10 11:32:57 +08:00

xpu_pre_and_post_process.py

[XPU] Fix PD + MTP (#6495)

2026-02-27 19:07:35 +08:00