{"record":{"id":"88add02a1c4083b9","repo":"vllm-project/vllm","slug":"this-model-does-not-support-runner-pooling-yo","errorCode":null,"errorMessage":"This model does not support `--runner pooling`. You can pass `--convert {convert_option} to adapt it into a pooling model.","messagePattern":"This model does not support `--runner pooling`\\. You can pass `--convert (.+?) to adapt it into a pooling model\\.","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"vllm/config/model.py","lineNumber":661,"sourceCode":"        if (\n            is_pooling_model\n            and not is_generative_model\n            and self.runner_type in (\"draft\", \"generate\")\n        ):\n            raise ValueError(\n                f\"Embedding models do not support `--runner {self.runner_type}`. \"\n                \"Use `--runner pooling` or `--runner auto` for embedding models.\"\n            )\n        if self.runner_type == \"generate\" and not is_generative_model:\n            generate_converts = _RUNNER_CONVERTS[\"generate\"]\n            if self.convert_type not in generate_converts:\n                # Currently we don't have any converters for generative models\n                raise ValueError(\"This model does not support `--runner generate`.\")\n        if self.runner_type == \"pooling\" and not is_pooling_model:\n            pooling_converts = _RUNNER_CONVERTS[\"pooling\"]\n            if self.convert_type not in pooling_converts:\n                convert_option = \"<\" + \"|\".join(pooling_converts) + \">\"\n                raise ValueError(\n                    \"This model does not support `--runner pooling`. \"\n                    f\"You can pass `--convert {convert_option} to adapt \"\n                    \"it into a pooling model.\"\n                )\n\n        # Note: Initialize these attributes early because transformers fallback\n        # may fail to load dynamic modules in child processes\n        model_info, arch = registry.inspect_model_cls(architectures, self)\n        self._model_info = model_info\n        self._architecture = arch\n        logger.info(\"Resolved architecture: %s\", arch)\n\n        # Set default tokenizer modes based on model architecture\n        if self.tokenizer_mode == \"auto\":\n            if self.model_impl == \"terratorch\":\n                self.tokenizer_mode = \"terratorch\"\n            elif arch == \"MoonshotKimiaForCausalLM\":\n                self.tokenizer_mode = \"kimi_audio\"","sourceCodeStart":643,"sourceCodeEnd":679,"githubUrl":"https://github.com/vllm-project/vllm/blob/c794754062d49a8fdb63ab3c5215b488b865030c/vllm/config/model.py#L643-L679","documentation":"Error \"This model does not support `--runner pooling`. You can pass `--convert {convert_option} to adapt it into a pooling model.\" thrown in vllm-project/vllm.","triggerScenarios":"Raised at vllm/config/model.py:661 when validation fails: This model does not support `--runner pooling`; pass --convert to adapt it into a pooling model. Typically triggered by an incompatible or incomplete vLLM configuration, an unsupported platform/backend combination, or a runtime resource/dependency that is missing.","commonSituations":"Commonly encountered at vllm/config/model.py:661 during vLLM startup/config validation or runtime setup when: (1) conflicting CLI flags or config fields are combined, (2) the current platform (CUDA/ROCm/CPU/XPU) or installed optional packages do not support the requested feature, or (3) a required value is absent or out of range. Resolve by correcting the configuration as described in the message, or by selecting a supported alternative.","solutions":["Pass --convert <option> shown in the error to adapt the model into a pooling model, or use --runner generate."],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"c794754062d49a8fdb63ab3c5215b488b865030c","analyzedAt":"2026-08-14T21:17:39.825Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}