Haonan Luo 1b9f351d21 Support GPT-OSS-BF16 (#4240) ...

* [Feature] AppendAtten support sinks & HEAD_DIM=64

* fix bug

* fix bug

* fix bug

* fix bug

* [Feature] support gpt-oss

* fix bug

* add mask

* support-gpt-oss

* support-gpt-oss

* fix long seq

* support wint8

* support wint8

* support wint8

* update test

* change sliding windows init pos

---------

Co-authored-by: ming1753 <ideaminghp@163.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>

2025-10-20 14:44:58 +08:00

..

graph_optimization

[SOT] Change warnings to errors and remove fallback operations (#4378)

2025-10-17 11:27:04 +08:00

guided_decoding

[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362)

2025-10-17 10:40:59 +08:00

layers

Support GPT-OSS-BF16 (#4240)

2025-10-20 14:44:58 +08:00

model_loader

[v1 loader]code style (#4204)

2025-09-23 19:36:00 +08:00

models

Support GPT-OSS-BF16 (#4240)

2025-10-20 14:44:58 +08:00

ops

[Intel HPU] Support intel hpu platform (#4161)

2025-09-24 12:27:50 +08:00

__init__.py

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

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

forward_meta.py

[Optimization] Fuse get_max_len and get_kv_max_len (#4369)

2025-10-13 20:35:00 +08:00

load_weight_utils.py

[v1 loader]code style (#4204)

2025-09-23 19:36:00 +08:00

pre_and_post_process.py

perf: optimize ZMQ communication with async queue and single-threaded… (#4444)

2025-10-16 15:46:26 +08:00

utils.py

check paddle version for v1 loader (#4473)

2025-10-17 17:25:03 +08:00