{"record":{"id":"9e3556572b5b4d36","repo":"sgl-project/sglang","slug":"unsupported-backend-backend-currently-only-su","errorCode":null,"errorMessage":"Unsupported backend: {backend},  currently only support  {self.SUPPORTED_BACKENDS}","messagePattern":"Unsupported backend: (.+?),  currently only support  (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"python/sglang/srt/layers/quantization/auto_round.py","lineNumber":89,"sourceCode":"    ) -> None:\n        super().__init__()\n        if weight_bits not in self.SUPPORTED_BITS:\n            raise ValueError(\n                f\"Unsupported weight_bits: {weight_bits}, \"\n                f\"currently only support  {self.SUPPORTED_BITS}\"\n            )\n        if data_type not in self.SUPPORTED_DTYPES:\n            raise ValueError(\n                f\"Unsupported data_type: {data_type},\"\n                f\" currently only support  {self.SUPPORTED_DTYPES}\"\n            )\n        if packing_format not in self.SUPPORTED_FORMATS:\n            raise ValueError(\n                f\"Unsupported packing_format: {packing_format}, \"\n                f\"currently only support  {self.SUPPORTED_FORMATS}\"\n            )\n        if backend not in self.SUPPORTED_BACKENDS:\n            raise ValueError(\n                f\"Unsupported backend: {backend},  \"\n                f\"currently only support  {self.SUPPORTED_BACKENDS}\"\n            )\n\n        self.weight_bits = weight_bits\n        self.group_size = group_size\n        self.sym = sym\n        self.packing_format = packing_format\n        self.block_name_to_quantize = (\n            block_name_to_quantize.split(\",\")\n            if isinstance(block_name_to_quantize, str)\n            else block_name_to_quantize\n        )\n        self.extra_config = extra_config\n        self.data_type = data_type\n        self.backend = backend\n        self.pack_factor = Fraction(32, weight_bits)\n        self.lm_head_quantized = lm_head_quantized","sourceCodeStart":71,"sourceCodeEnd":107,"githubUrl":"https://github.com/sgl-project/sglang/blob/0132848349585cfe6aae51c4941cbae872505f8a/python/sglang/srt/layers/quantization/auto_round.py#L71-L107","documentation":"AutoRoundConfig validates the inference backend string against SUPPORTED_BACKENDS (e.g. 'auto', 'ipex', 'deepspeed', custom triton kernels). An unknown backend value raises at config load.","triggerScenarios":"Passing backend='something' when constructing AutoRoundConfig, or a checkpoint quantization_config embedding a backend name SGLang doesn't know.","commonSituations":"Newer AutoRound export tools emitting new backend names, or hand-tuning config.json for a specific runtime.","solutions":["Use 'auto' or one of the names in SUPPORTED_BACKENDS","Upgrade SGLang so the backend is registered","Re-export the model with default backend"],"exampleFix":"// before\n\"quantization_config\": {\"backend\": \"itrex\", ...}\n// after\n\"quantization_config\": {\"backend\": \"auto\", ...}","handlingStrategy":"validation","validationCode":"be = quant_cfg.get(\"backend\", \"auto\")\nassert be in AutoRoundConfig.SUPPORTED_BACKENDS or be == \"auto\"","typeGuard":"def is_supported_backend(b: str) -> bool:\n    return b in AutoRoundConfig.SUPPORTED_BACKENDS","tryCatchPattern":null,"preventionTips":["Leave backend as 'auto' unless targeting a specific runtime","Pin SGLang version matching the exporter"],"tags":["quantization","auto-round","backend"],"backgroundTag":"invalid-configuration-value","analyzedSha":"0132848349585cfe6aae51c4941cbae872505f8a","analyzedAt":"2026-08-28T05:10:05.995Z","schemaVersion":2},"datasetVersion":"2026-08-28T06:17:29.519Z"}