{
  "schema": "anvil-serving.llm-qualification-configuration/v1",
  "model": "ormandj/GLM-5.3-Flash-W4A16-NVFP4-K32-Experts-FP8-WO",
  "revision": "c3cbb9891b67c741bcbf6b176dd7af9265b069db",
  "image": "ghcr.io/ormandj/sglang-glm53-flash-sm120@sha256:0c0637959c3931829f05154087bbefd2c50003fb9b2010200ce0ec82f4d71a53",
  "served_model": "glm53-flash-ormandj-sglang-sm120-tp2-393k-c1-adaptive-mtp",
  "os": "Linux-7.0.0-31-generic-x86_64-with-glibc2.43",
  "repository_revision": "8abcc5dc75a1b2389210b553120abb76e5864d3a",
  "declared_serve_flags": [
    "--served-model-name glm53-flash-ormandj-sglang-sm120-tp2-393k-c1-adaptive-mtp",
    "--tp-size 2",
    "--quantization modelopt_mixed",
    "--enable-multimodal",
    "--image-processor-backend torchvision",
    "--mm-process-config '{\"image\":{\"max_image_tokens\":3072}}'",
    "--warmups serving_coverage",
    "--moe-runner-backend flashinfer_cutlass",
    "--disable-shared-experts-fusion",
    "--disable-custom-all-reduce",
    "--attention-backend dsa",
    "--linear-attn-backend triton",
    "--dsa-prefill-backend flashinfer_sparse_mla",
    "--dsa-decode-backend flashinfer_sparse_mla",
    "--kv-cache-dtype fp8_e4m3",
    "--mamba-ssm-dtype bfloat16",
    "--context-length 393216",
    "--max-total-tokens 393216",
    "--mem-fraction-static 0.99",
    "--chunked-prefill-size 4096",
    "--max-prefill-tokens 4096",
    "--max-running-requests 1",
    "--max-mamba-cache-size 5",
    "--cuda-graph-max-bs-decode 1",
    "--speculative-algorithm EAGLE",
    "--speculative-num-steps 5",
    "--speculative-eagle-topk 1",
    "--speculative-num-draft-tokens 6",
    "--speculative-adaptive",
    "--speculative-adaptive-config /tmp/glm53-adaptive.json",
    "--reasoning-parser glm45",
    "--tool-call-parser glm47",
    "--enable-metrics",
    "--enable-cache-report",
    "--host 0.0.0.0",
    "--port 8001"
  ],
  "transport_controls": {
    "CUDA_DEVICE_ORDER": "PCI_BUS_ID",
    "NCCL_CUMEM_ENABLE": "0",
    "NCCL_DEBUG": "INFO",
    "NCCL_P2P_DISABLE": "1"
  },
  "runtime_identity_verified": "managed recipe status + native models/model-info",
  "comparison_differences": [
    "Linux host/driver/runtime and NCCL_P2P_DISABLE=1",
    "host port and cache volume labels",
    "Benchmark runner revision differs; prompt bytes and actual prompt token counts verified against historical runner in prompt-equivalence.json"
  ],
  "promotion_authorized": false,
  "oci_build_revision": "a547c90c74f1363920287eb80adc88a16d1e7005",
  "oci_build_revision_source": "narrow read-only image metadata inspection, matches historical image metadata"
}