|
|
"--max-model-len", "393216",
|
|
"--max-model-len", "393216",
|
|
|
"--max-num-batched-tokens", "8192",
|
|
"--max-num-batched-tokens", "8192",
|
|
|
'{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"],"cudagraph_capture_sizes":[1,2,3,4,5,6,7,8]}'""",
|
|
'{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"],"cudagraph_capture_sizes":[1,2,3,4,5,6,7,8]}'""",
|