Qwen3-8B-FP8 / hf_quant_config.json

Initial commit

2cebc4c about 1 year ago

240 Bytes

{
    "producer": {
        "name": "modelopt",
        "version": "0.35.0"
    },
    "quantization": {
        "quant_algo": "FP8",
        "kv_cache_quant_algo": "FP8",
        "exclude_modules": [
            "lm_head"
        ]
    }
}

	{
	"producer": {
	"name": "modelopt",
	"version": "0.35.0"
	},
	"quantization": {
	"quant_algo": "FP8",
	"kv_cache_quant_algo": "FP8",
	"exclude_modules": [
	"lm_head"
	]
	}
	}