Liangsheng YinandBrayden Zhong aea78d1e73 [misc] Pass FP8 scales in FlashInfer SWA prefill, autotune fp8 on SM120, and tighten is_image_understandable_model (#34217) ...

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>

2026-08-09 23:45:11 -07:00

..

torch_ops

[NPU]: Optimize xgrammar token bitmask on NPU with AscendC (#24133)

2026-05-28 21:38:06 -07:00

base_grammar_backend.py

config: stop writing config onto the published ServerArgs at three sites (#33334)

2026-08-02 21:22:05 -07:00

grammar_manager.py

[Fix] Treat an empty grammar constraint as unset in SamplingParams (#33328)

2026-08-02 21:45:51 -07:00

llguidance_backend.py

Use native batched llguidance mask generation (#32412)

2026-07-25 16:36:32 -07:00

outlines_backend.py

fix: propagate grammar errors and improve llguidance backend (#20467)

2026-03-15 16:11:18 -07:00

outlines_jump_forward.py

Organize spec-related data structures (#10735)

2025-10-01 09:45:30 +08:00

reasoner_grammar_backend.py

[Kimi K3] Add reasoning, tool-call, and OpenAI serving support (#33025)

2026-08-01 14:57:23 -07:00

utils.py

[Feature] New structural tag support (#10691)

2025-10-20 18:25:58 +08:00

xgrammar_backend.py

[misc] Pass FP8 scales in FlashInfer SWA prefill, autotune fp8 on SM120, and tighten is_image_understandable_model (#34217)

2026-08-09 23:45:11 -07:00