Baizhou Zhang efbae697b3 [Revision] Replace enable_flashinfer_mla argument with attention_backend (#5052)

2025-04-05 01:23:02 -07:00

..

cuda_graph_runner.py

[Fix] avoid stream sync and torch compile in prefill for fa3 backend (#4932)

2025-03-30 13:53:44 -07:00

forward_batch_info.py

FA3 Spec Decoding to support top k = 1 and add cuda graph support (#5050)

2025-04-04 23:03:59 -07:00

model_runner.py

[Revision] Replace enable_flashinfer_mla argument with attention_backend (#5052)

2025-04-05 01:23:02 -07:00