Liangsheng Yin c0f1f7e062 [Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)

2026-07-13 13:47:53 -05:00

..

__init__.py

Enable Breakable Cuda Graph as Default (#29458)

2026-07-01 22:04:44 -07:00

base_cuda_graph_runner.py

[Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)

2026-07-13 13:47:53 -05:00

base_runner.py

[Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)

2026-07-13 13:47:53 -05:00

decode_cuda_graph_runner.py

[Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)

2026-07-13 13:47:53 -05:00

eager_runner.py

[Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)

2026-07-13 13:47:53 -05:00

flashinfer_autotune.py

[Spec] Enable FlashInfer autotune for spec draft (#29595)

2026-07-01 13:36:07 -07:00

prefill_cuda_graph_runner.py

Enable breakable prefill CUDA graph for DP attention (#30898)

2026-07-12 17:10:04 -07:00

shape_key.py

[Tiny] Cuda Graph Refactor Code Style Follow up (#28107)

2026-06-12 18:38:13 -07:00