{"record":{"id":"068fcf03e462d1f1","repo":"vllm-project/vllm","slug":"cudagraphmode-cudagraph-mode-name-is-not-support-068fcf","errorCode":null,"errorMessage":"CUDAGraphMode.{cudagraph_mode.name} is not supported with {min_cg_attn_backend} backend (support:{min_cg_support}) ; please try cudagraph_mode=PIECEWISE, and make sure compilation mode is VLLM_COMPILE","messagePattern":"CUDAGraphMode\\.(.+?) is not supported with (.+?) backend \\(support:(.+?)\\) ; please try cudagraph_mode=PIECEWISE, and make sure compilation mode is VLLM_COMPILE","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"vllm/config/compilation.py","lineNumber":1467,"sourceCode":"                f\"CUDAGraphMode.{cudagraph_mode.name} is not supported\"\n                f\" with spec-decode for attention backend \"\n                f\"{min_cg_attn_backend} (support: {min_cg_support})\"\n            )\n            if self.splitting_ops_contain_attention():\n                msg += \"; setting cudagraph_mode=PIECEWISE\"\n                cudagraph_mode = CUDAGraphMode.PIECEWISE\n            else:\n                msg += \"; setting cudagraph_mode=NONE\"\n                cudagraph_mode = CUDAGraphMode.NONE\n            logger.warning(msg)\n\n        # double check that we can support full cudagraph if they are requested\n        # even after automatic downgrades\n        if (\n            cudagraph_mode.has_full_cudagraphs()\n            and min_cg_support == AttentionCGSupport.NEVER\n        ):\n            raise ValueError(\n                f\"CUDAGraphMode.{cudagraph_mode.name} is not \"\n                f\"supported with {min_cg_attn_backend} backend (\"\n                f\"support:{min_cg_support}) \"\n                \"; please try cudagraph_mode=PIECEWISE, \"\n                \"and make sure compilation mode is VLLM_COMPILE\"\n            )\n\n        # MRV1 adjusts cudagraph sizes to be a multiple of uniform_decode_query_len\n        # to avoid: https://github.com/vllm-project/vllm/issues/28207 and temp-fix:\n        # https://github.com/vllm-project/vllm/issues/28207#issuecomment-3504004536\n        # Will be removed in the near future when we have separate cudagraph capture\n        # sizes for decode and mixed prefill-decode.\n        # MRV2 handles cudagraph capture sizing in cudagraph_utils.py\n        # and doesn't need below: https://github.com/vllm-project/vllm/pull/45953\n        if (\n            not use_v2_model_runner\n            and cudagraph_mode.decode_mode() == CUDAGraphMode.FULL\n            and uniform_decode_query_len > 1","sourceCodeStart":1449,"sourceCodeEnd":1485,"githubUrl":"https://github.com/vllm-project/vllm/blob/c794754062d49a8fdb63ab3c5215b488b865030c/vllm/config/compilation.py#L1449-L1485","documentation":"Error \"CUDAGraphMode.{cudagraph_mode.name} is not supported with {min_cg_attn_backend} backend (support:{min_cg_support}) ; please try cudagraph_mode=PIECEWISE, and make sure compilation mode is VLLM_COMPILE\" thrown in vllm-project/vllm.","triggerScenarios":"Raised at vllm/config/compilation.py:1467 when validation fails: CUDAGraphMode not supported with the selected attention backend; try cudagraph_mode=PIECEWISE with compilation mode VLLM_COMPILE. 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/compilation.py:1467 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":["Set cudagraph_mode=PIECEWISE in the compilation config.","Ensure compilation mode is VLLM_COMPILE (-O3).","Or select an attention backend with stronger CUDA graph support."],"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"}