Xinyuan Tong 0bfe1d145c fa3 & trtllm_mha spec overlap (#11874)

2025-10-31 17:38:13 -07:00

..

cpu_graph_runner.py

Tiny move files to utils folder (#11166)

2025-10-03 22:40:06 +08:00

cuda_graph_runner.py

[Bug fix] [PP] fix wrong dtype for quantified model (#12247)

2025-10-28 01:27:24 -07:00

forward_batch_info.py

fa3 & trtllm_mha spec overlap (#11874)

2025-10-31 17:38:13 -07:00

model_runner.py

Support Kimi Linear (#12469)

2025-10-31 14:03:35 -07:00

npu_graph_runner.py

[Feature] Support DeepSeek MTP on NPU (#11897)

2025-10-30 21:56:56 +08:00

piecewise_cuda_graph_runner.py

[Fix] fix allreduce bug in Piecewise Graph (#12106)

2025-10-26 21:15:48 +08:00