File size: 1,969 Bytes
76459e3 a6bafbc 76459e3 a6bafbc 76459e3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | {
"config_groups": {
"group_0": {
"targets": [
"Linear"
],
"weights": {
"num_bits": 8,
"type": "float",
"symmetric": true,
"group_size": 32,
"strategy": "group",
"block_structure": null,
"dynamic": false,
"actorder": null,
"scale_dtype": "torch.uint8",
"zp_dtype": null,
"observer": "memoryless_minmax",
"observer_kwargs": {}
},
"input_activations": {
"num_bits": 8,
"type": "float",
"symmetric": true,
"group_size": 32,
"strategy": "group",
"block_structure": null,
"dynamic": true,
"actorder": null,
"scale_dtype": "torch.uint8",
"zp_dtype": null,
"observer": null,
"observer_kwargs": {}
},
"output_activations": null,
"format": null
},
"group_1": {
"targets": [
"Qwen3Attention"
],
"weights": null,
"input_activations": {
"num_bits": 8,
"type": "float",
"symmetric": true,
"group_size": null,
"strategy": "tensor",
"block_structure": null,
"dynamic": false,
"actorder": null,
"scale_dtype": null,
"zp_dtype": null,
"observer": "memoryless_minmax",
"observer_kwargs": {}
},
"output_activations": null,
"format": null
}
},
"quant_method": "compressed-tensors",
"kv_cache_scheme": {
"num_bits": 8,
"type": "float",
"symmetric": true,
"group_size": null,
"strategy": "tensor",
"block_structure": null,
"dynamic": false,
"actorder": null,
"scale_dtype": null,
"zp_dtype": null,
"observer": "memoryless_minmax",
"observer_kwargs": {}
},
"format": "mxfp8-quantized",
"quantization_status": "compressed",
"global_compression_ratio": null,
"ignore": [
"lm_head"
],
"provider": "auto-round"
} |