{"record":{"id":"6f8154e8df1f5b73","repo":"vllm-project/vllm","slug":"cumem-allocator-is-not-supported-on-current-platfo","errorCode":null,"errorMessage":"cumem allocator is not supported on current platform.","messagePattern":"cumem allocator is not supported on current platform\\.","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"vllm/config/model.py","lineNumber":606,"sourceCode":"            self.tokenizer_revision = resolve_revision(\n                self.tokenizer,\n                self.tokenizer_revision,\n                self.hf_token,\n            )\n\n        if self.enable_sleep_mode:\n            if not current_platform.is_sleep_mode_available():\n                raise ValueError(\"Sleep mode is not supported on current platform.\")\n            if current_platform.is_cuda_alike() and not self.enable_cumem_allocator:\n                logger.info_once(\n                    \"Enabling cumem allocator because sleep mode requires it.\"\n                )\n                self.enable_cumem_allocator = True\n        if (\n            self.enable_cumem_allocator\n            and not current_platform.is_cumem_allocator_available()\n        ):\n            raise ValueError(\"cumem allocator is not supported on current platform.\")\n\n        hf_config = get_config(\n            self.hf_config_path or self.model,\n            self.trust_remote_code,\n            self.revision,\n            self.code_revision,\n            self.config_format,\n            hf_overrides_kw=hf_overrides_kw,\n            hf_overrides_fn=hf_overrides_fn,\n            token=self.hf_token,\n        )\n        self.hf_config = hf_config\n        if dict_overrides:\n            self._apply_dict_overrides(hf_config, dict_overrides)\n        self.hf_text_config = get_hf_text_config(self.hf_config)\n        self.model_arch_config = self.get_model_arch_config()\n        self.attention_chunk_size = getattr(\n            self.hf_text_config, \"attention_chunk_size\", None","sourceCodeStart":588,"sourceCodeEnd":624,"githubUrl":"https://github.com/vllm-project/vllm/blob/c794754062d49a8fdb63ab3c5215b488b865030c/vllm/config/model.py#L588-L624","documentation":"Error \"cumem allocator is not supported on current platform.\" thrown in vllm-project/vllm.","triggerScenarios":"Raised at vllm/config/model.py:606 when validation fails: cumem allocator is not supported on current platform.. 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:606 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":["Do not enable the cumem allocator on the current platform.","Run on a platform that supports cuMem (CUDA) if the allocator is required."],"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":"2026-08-15T17:31:12.345Z"}