{ "producer": { "name": "modelopt", "version": "0.45.0.dev127+ga3a02ca5b.d20260608" }, "quantization": { "quant_algo": "NVFP4", "kv_cache_quant_algo": "FP8", "group_size": 16, "exclude_modules": [ "lm_head", "*embed_vision*", "*mlp*", "*router*", "*self_attn*", "*self_conditioning*", "*vision_tower*" ] } }