Xinyu Chen ffb3d553cc [Model Runner V2] Init cuda graph pool when necessary (#33217) ...

Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>

2026-02-11 09:12:13 -08:00

..

__init__.py

[ModelRunner V2] Misc minor simplifications and optimizations (#33467)

2026-02-01 22:17:14 +00:00

eagle_cudagraph.py

[Model Runner V2] Init cuda graph pool when necessary (#33217)

2026-02-11 09:12:13 -08:00

eagle.py

[ModelRunner V2][BugFix] Fix max_query_len calculation (#34167)

2026-02-09 21:47:17 +00:00

rejection_sample.py

[Model Runner V2] Implement get_num_sampled_and_rejected kernel (#30029)

2025-12-04 07:19:42 -08:00

utils.py

[Core] Don't schedule spec tokens with prefill chunks (#33652)

2026-02-04 23:40:22 +00:00