vllm-project/vllm · error · ValueError

All encoder_cudagraph_token_budgets must be positive, got {s

Error message

All encoder_cudagraph_token_budgets must be positive, got {self.encoder_cudagraph_token_budgets}

What it means

Error "All encoder_cudagraph_token_budgets must be positive, got {self.encoder_cudagraph_token_budgets}" thrown in vllm-project/vllm.

Source

Thrown at vllm/config/compilation.py:1055

        ):
            raise ValueError(
                "encoder_cudagraph_max_vision_items_per_batch must be "
                "non-negative (0 = auto-infer)"
            )
        if (
            self.cudagraph_mm_encoder
            and self.encoder_cudagraph_max_frames_per_batch is not None
            and self.encoder_cudagraph_max_frames_per_batch < 0
        ):
            raise ValueError(
                "encoder_cudagraph_max_frames_per_batch must be "
                "non-negative (None = auto-infer)"
            )

        if self.encoder_cudagraph_token_budgets and any(
            b <= 0 for b in self.encoder_cudagraph_token_budgets
        ):
            raise ValueError(
                f"All encoder_cudagraph_token_budgets must be positive, "
                f"got {self.encoder_cudagraph_token_budgets}"
            )

        if self.backend == "":
            self.backend = current_platform.get_compile_backend()

    def init_backend(
        self,
        vllm_config: "VllmConfig",
        prefix: str = "",
        is_encoder: bool = False,
    ) -> str | Callable:
        """
        Initialize the backend for the compilation config from a vllm config.
        Arguments:
            vllm_config: The vllm config to initialize the backend from.
            prefix: Cache directory prefix for this compiled module.

View on GitHub (pinned to c794754062)

Solutions

1. Make every entry in encoder_cudagraph_token_budgets a positive integer, or omit the option entirely.

When it happens

Trigger: Raised at vllm/config/compilation.py:1055 when validation fails: All encoder_cudagraph_token_budgets must be positive. Typically triggered by an incompatible or incomplete vLLM configuration, an unsupported platform/backend combination, or a runtime resource/dependency that is missing.

Common situations: Commonly encountered at vllm/config/compilation.py:1055 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.

AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14). Data as JSON: /api/errors/7d6f2c9a6a98046c. Report an issue: GitHub.