{"record":{"id":"7d401fedaa82ae12","repo":"sgl-project/sglang","slug":"component-name-r-does-not-support-an-explicit-qu","errorCode":null,"errorMessage":"{component_name!r} does not support an explicit quantization override; use a self-describing quantized component checkpoint when supported","messagePattern":"(.+?) does not support an explicit quantization override; use a self-describing quantized component checkpoint when supported","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"python/sglang/multimodal_gen/runtime/loader/component_loaders/component_loader.py","lineNumber":238,"sourceCode":"        component_model_path: str,\n        server_args: ServerArgs,\n        component_name: str,\n        transformers_or_diffusers: str,\n    ) -> tuple[AutoModel, float]:\n        \"\"\"\n        Template method that standardizes logging around the core load implementation.\n        The priority of loading method is:\n            1. load customized component\n            2. load native diffusers/transformers component\n        If all of the above methods failed, an error will be thrown\n\n        \"\"\"\n        component_quantization = server_args.component_quantizations.get(component_name)\n        if (\n            component_quantization is not None\n            and not self.supports_online_quantization_override\n        ):\n            raise ValueError(\n                f\"{component_name!r} does not support an explicit quantization \"\n                \"override; \"\n                \"use a self-describing quantized component checkpoint when supported\"\n            )\n\n        gpu_mem_before_loading = current_platform.get_available_gpu_memory()\n        logger.info(\n            \"Loading %s from %s. avail mem: %.2f GB\",\n            component_name,\n            component_model_path,\n            gpu_mem_before_loading,\n        )\n        attn_backend = None\n        component_attn_name = None\n        if get_component_attn_backend_context() is None:\n            attn_backend, matched_backend_key = (\n                server_args.resolve_component_attention_backend(component_name)\n            )","sourceCodeStart":220,"sourceCodeEnd":256,"githubUrl":"https://github.com/sgl-project/sglang/blob/0132848349585cfe6aae51c4941cbae872505f8a/python/sglang/multimodal_gen/runtime/loader/component_loaders/component_loader.py#L220-L256","documentation":"ComponentLoader.load rejects an explicit per-component quantization override (server_args.component_quantizations[name]) when the loader does not set supports_online_quantization_override. Such components must instead ship as self-describing pre-quantized checkpoints.","triggerScenarios":"Launching with a server args entry like component_quantizations={'text_encoder': 'fp8'} for a component whose loader class has supports_online_quantization_override = False (default).","commonSituations":"Copy-pasting CLI flags for on-the-fly quantization onto a component (e.g. an adapter or bridge) that only accepts serialized quantized weights; enabling quantization globally and having it inherited by unsupported components.","solutions":["Remove the quantization override for that component from server args / CLI config","Use a checkpoint that is already quantized on disk (self-describing quantization_config)","If you are the loader author and the component genuinely supports online quantization, set supports_online_quantization_override = True on the loader"],"exampleFix":"# before\nserver_args.component_quantizations['text_encoder'] = 'fp8'\n# after\ndel server_args.component_quantizations['text_encoder']  # use pre-quantized fp8 checkpoint","handlingStrategy":"validation","validationCode":"assert name not in server_args.component_quantizations or loader.supports_online_quantization_override, \\\n    f\"{name} does not accept quantization overrides\"","typeGuard":null,"tryCatchPattern":null,"preventionTips":["Only set component_quantizations for components whose loaders advertise override support","Prefer self-describing quantized checkpoints over runtime overrides"],"tags":["quantization","server-args","config","model-loading"],"backgroundTag":"unsupported-quantization-override","analyzedSha":"0132848349585cfe6aae51c4941cbae872505f8a","analyzedAt":"2026-08-28T05:10:05.995Z","schemaVersion":2},"datasetVersion":"2026-08-28T06:17:29.519Z"}