{ | |
"batcher": null, | |
"cacher": null, | |
"compiler": "torch_compile", | |
"pruner": null, | |
"quantizer": null, | |
"torch_compile_backend": "inductor", | |
"torch_compile_batch_size": 1, | |
"torch_compile_dynamic": null, | |
"torch_compile_fullgraph": true, | |
"torch_compile_make_portable": false, | |
"torch_compile_max_kv_cache_size": 400, | |
"torch_compile_mode": "default", | |
"torch_compile_seqlen_manual_cuda_graph": 100, | |
"max_batch_size": 1, | |
"device": "cpu", | |
"save_fns": [ | |
"save_before_apply" | |
], | |
"load_fns": [ | |
"transformers" | |
], | |
"reapply_after_load": { | |
"pruner": null, | |
"quantizer": null, | |
"cacher": null, | |
"compiler": "torch_compile", | |
"batcher": null | |
} | |
} |