Qiaolin Yu 4a4772ae03 Support speculative decoding in hybrid attention backend (#9573)

2025-08-28 01:11:42 -07:00

..

cuda_graph_runner.py

remove redundant rank0_log function. (#9560)

2025-08-24 23:17:55 -07:00

forward_batch_info.py

Support MHA with chunked prefix cache for flashinfer/flashmla backend, support page size > 1 for MHA chunked prefix (#8616)

2025-08-21 18:19:44 -07:00

model_runner.py

Support speculative decoding in hybrid attention backend (#9573)

2025-08-28 01:11:42 -07:00

npu_graph_runner.py

[feature] Ascend NPU graph support (#9399)

2025-08-20 21:13:27 -07:00