Stefan HeandBinyao Jiang 6c18ab46a2 [Qwen3-Next] switch to triton and cache conv states to accelerate MTP from 300 tok/s to 341 tok/s (#10335) ...

Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>

2025-09-11 11:59:48 -07:00

..

build_eagle_tree.py

Add treemask mode to build_eagle_tree & release sgl-kernel 0.2.3 (#7756)

2025-07-05 12:17:05 -07:00

eagle_draft_cuda_graph_runner.py

Qwen2.5-VL eagle3 infer (#8801)

2025-09-07 20:44:34 -07:00

eagle_draft_extend_cuda_graph_runner.py

Standalone speculative decoding (#10090)

2025-09-07 20:55:09 -07:00

eagle_utils.py

[MTP] Force greedy sampling on AMD (#9127)

2025-08-22 11:14:43 -07:00

eagle_worker.py

[Qwen3-Next] switch to triton and cache conv states to accelerate MTP from 300 tok/s to 341 tok/s (#10335)

2025-09-11 11:59:48 -07:00

spec_info.py

Standalone speculative decoding (#10090)

2025-09-07 20:55:09 -07:00

standalone_worker.py

Standalone speculative decoding (#10090)

2025-09-07 20:55:09 -07:00