5 people d82e339ce2 [Session R3] Add routed_experts_start_len for absolute routing slice control (#24851) ...

Co-authored-by: Byron Hsu <byron@periodiclabs.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: zyzshishui <zyzshishui@gmail.com>
Co-authored-by: Yuzhen Zhou <82826991+zyzshishui@users.noreply.github.com>

2026-05-10 10:04:43 -07:00

..

__init__.py

move topk capturers to srt/state_capturer/ (#24450)

2026-05-05 15:54:01 -07:00

base.py

[Session R3] Add routed_experts_start_len for absolute routing slice control (#24851)

2026-05-10 10:04:43 -07:00

indexer_topk.py

move topk capturers to srt/state_capturer/ (#24450)

2026-05-05 15:54:01 -07:00

routed_experts.py

[R3] Avoid implicit CUDA sync in routed experts DP slicing (#24550)

2026-05-06 18:37:36 -07:00