axquant_runtime.json

{
  "ax_engine": {
    "decode_kernel": null,
    "fused_mtp": null,
    "kernel_evidence": "unmeasured",
    "model_manifest": "model-manifest.json",
    "preferred_group_size": 32
  },
  "compatible_runtimes": [],
  "created_at": "2026-08-05T21:28:44.608826Z",
  "kv_cache": null,
  "memory_policy": {
    "kv_cache_precision": "runtime-default",
    "mtp_buffers": "not-required",
    "prefix_cache": "runtime-managed",
    "unified_memory_safety_margin": "benchmark-required"
  },
  "mtp": {
    "acceptance_retention": null,
    "detected": false,
    "draft_tokens": null,
    "enabled_by_default": false,
    "head_precision": null,
    "measured_speedup": null,
    "optimized": false,
    "recommended_temperature_max": null,
    "sidecar_file": null,
    "verification_mode": null
  },
  "optimization_scope": "text-path",
  "primary_runtime": {
    "compatibility_level": "A",
    "manifest": "config.json",
    "mtp_support": "none",
    "name": "mlx-audio",
    "notes": [
      "MLX-Audio loads the protected modality tower and AXQ language decoder."
    ],
    "standard_inference": true,
    "standard_mlx_weights": true,
    "support_level": "standard-inference"
  },
  "schema_version": "axquant.runtime.v1"
}