config.json

{
  "dfloat11_config": {
    "bytes_per_thread": 8,
    "pattern_dict": {
      "blocks\\.\\d+": [
        "attn1.to_q",
        "attn1.to_k",
        "attn1.to_v",
        "attn1.to_out.0",
        "attn2.to_q",
        "attn2.to_k",
        "attn2.to_v",
        "attn2.to_out.0",
        "ffn.net.0.proj",
        "ffn.net.2"
      ]
    },
    "threads_per_block": [
      512
    ],
    "version": "0.2.0"
  },
  "model_type": "llama"
}