{ | |
"parameters": { | |
"max_total_tokens": 2048, | |
"max_input_length": 1024, | |
"max_batch_total_tokens": 8192, | |
"max_concurrent_requests": 1, | |
"max_best_of": 1, | |
"max_stop_sequences": 4, | |
"max_batch_size": 1, | |
"waiting_served_ratio": 1.2 | |
}, | |
"hardware": { | |
"task_type": "text-generation", | |
"accelerator": "gpu", | |
"num_gpus": 1, | |
"gpu_memory_gb": 24, | |
"distributed_setup": false | |
}, | |
"framework_type": "pytorch", | |
"torch_compile": false, | |
"trust_remote_code": true, | |
"disable_custom_kernels": true | |
} |