Lianmin Zheng 86e0dde555 Improve the user control of new_token_ratio (#1811)

2024-10-26 16:39:41 -07:00

..

cuda_graph_runner.py

Improve the user control of new_token_ratio (#1811)

2024-10-26 16:39:41 -07:00

forward_batch_info.py

Qwen2vl support cuda graph and disable radix cache (#1780)

2024-10-25 10:45:17 -04:00

model_runner.py

Qwen2vl support cuda graph and disable radix cache (#1780)

2024-10-25 10:45:17 -04:00