Loaded 2379 saved tensors; all 1199 source tensors accounted for.
All 609 unquantized tensors equal the original BF16 values.
CPU inference uses FP32 floating values; saved 4-bit weights are unchanged.
Hello from Swift.
Text generation passed.
Real-weight MTP step passed.
Real-weight vision encoder passed.
{
  "status": "PASS",
  "recorded_at": "2026-09-21T18:14:21.887850+00:00",
  "source_repo": "ukisai/Swift-1.5-Qwen3.8-27b",
  "source_revision": "00ccd14e006897d28cb0ed5bf26390e60d274251",
  "source_shards": 18,
  "source_shard_bytes": 55563006776,
  "source_tensors": 1199,
  "mapped_source_tensors": 1199,
  "saved_tensors": 2379,
  "categories": {
    "text": 851,
    "MTP": 15,
    "vision": 333
  },
  "ignored_tensors": 0,
  "unexplained_tensors": 0,
  "exact_unquantized_tensors": 609,
  "quantization": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine"
  },
  "all_floating_tensors_finite": true,
  "tokenizer": "Qwen2Tokenizer",
  "processor": "Qwen3VLProcessor",
  "assets_sha256": {
    "generation_config.json": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e",
    "preprocessor_config.json": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
    "video_preprocessor_config.json": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13",
    "tokenizer.json": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3",
    "tokenizer_config.json": "b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27",
    "vocab.json": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003",
    "merges.txt": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d",
    "chat_template.jinja": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041"
  },
  "chat_templates": [
    {
      "options": {
        "enable_thinking": false
      },
      "rendered": "<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
    },
    {
      "options": {
        "reasoning_effort": "low"
      },
      "rendered": "<|im_start|>system\nReasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.<|im_end|>\n<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n"
    },
    {
      "options": {
        "reasoning_effort": "xhigh"
      },
      "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n"
    }
  ],
  "load_seconds": 3.351265648000208,
  "load_memory_bytes": 15826466152,
  "process_peak_rss_bytes": 21142360064,
  "inference_floating_dtype": "float32, CPU runtime only; stored floating tensors remain BF16",
  "native_bf16_cpu_inference": "Aborted after reproducing incorrect accumulation in the official Linux BF16 quantized matmul. See cpu-quantized-matmul-diagnostic.json.",
  "generation": {
    "prompt": "<|im_start|>user\nReply with exactly: Hello from Swift.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n",
    "text": "Hello from Swift.",
    "token_ids": [
      9419,
      494,
      22929,
      13,
      248046
    ],
    "tokens": 5,
    "tokens_per_second": 0.0797672292904007,
    "prompt_tokens_per_second": 0.06443886297275572,
    "elapsed_seconds": 374.00736365800003,
    "finish_reason": "stop"
  },
  "mtp": {
    "status": "PASS",
    "shape": [
      1,
      1,
      248320
    ],
    "path": "Explicit MTP step with real text hidden states and shared LM head; speculative generation is not integrated"
  },
  "vision": {
    "status": "PASS",
    "shape": [
      64,
      5120
    ],
    "grid": [
      [
        1,
        16,
        16
      ]
    ],
    "path": "Vision encoder only; image/video insertion and multimodal text generation are not implemented"
  },
  "total_validation_seconds": 467.15810263900016
}