{
  "schema_version": 1,
  "package_type": "paiton-compiled-runtime-overlay",
  "repo_id": "EliovpAI/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit-Paiton-RDNA4",
  "release_version": "v1.0.0",
  "weights_included": false,
  "base_model": {
    "repo_id": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit",
    "revision": "4bd30395b72ea6045edd04806c4fea448d4467b3"
  },
  "runtime_image": "ghcr.io/eliovp/paiton-vllm-plugin:qwen3-coder-30b-awq-rdna4-v1.0.0",
  "runtime_image_digest": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:fb47f4ab6073da943e553849985c81326e33b425e1017f97f3f79fad09586a8e",
  "public_source": {
    "repository": "https://github.com/Eliovp-BV/paiton-vllm-plugin",
    "commit": "9148505697c70ed3e0a68f298ca6860579db0fbb"
  },
  "artifact_origin": "published Qwen3-Coder v1.0.0 release; identical to the artifact bundled in the runtime image",
  "contract": {
    "gpu": "AMD Radeon AI PRO R9700",
    "gpu_arch": "gfx1201",
    "compute_units": 64,
    "workgroup_processors": 32,
    "max_concurrent_sequences": 2,
    "max_model_len": 4096,
    "quantization": "compressed-tensors symmetric INT4 G32",
    "activations": "bfloat16"
  },
  "files": [
    {
      "path": "overlay/qwen3_coder_moe_w4a16_g32_gfx1201.json",
      "size_bytes": 1050,
      "sha256": "83284e476ce918726e0e216d8c29b9b7326061306380b7c875d6625b16872769"
    },
    {
      "path": "overlay/qwen3_coder_moe_w4a16_g32_gfx1201.so",
      "size_bytes": 336128,
      "sha256": "74fb7015e285d3b7863fc8f54341204a252a2ab305921edd5b30f5724915958f"
    }
  ]
}