vllm-project/vllm · error · ValueError

Dual CUDA streams are only supported on CUDA platforms.

Error message

Dual CUDA streams are only supported on CUDA platforms.

What it means

Error "Dual CUDA streams are only supported on CUDA platforms." thrown in vllm-project/vllm.

Source

Thrown at vllm/config/lora.py:126

        # target_modules affects which modules get LoRA applied
        factors.append(
            tuple(sorted(self.target_modules)) if self.target_modules else None
        )

        hash_str = safe_hash(str(factors).encode(), usedforsecurity=False).hexdigest()
        return hash_str

    @model_validator(mode="after")
    def _validate_lora_config(self) -> Self:
        if self.max_cpu_loras is None:
            self.max_cpu_loras = self.max_loras
        elif self.max_cpu_loras < self.max_loras:
            raise ValueError(
                f"max_cpu_loras ({self.max_cpu_loras}) must be >= "
                f"max_loras ({self.max_loras})."
            )
        if envs.VLLM_LORA_ENABLE_DUAL_STREAM and not current_platform.is_cuda_alike():
            raise ValueError("Dual CUDA streams are only supported on CUDA platforms.")
        if envs.VLLM_LORA_ENABLE_DUAL_STREAM and self.fully_sharded_loras:
            logger.warning_once(
                "fully_sharded_loras isn't compatible with "
                "VLLM_LORA_ENABLE_DUAL_STREAM, set VLLM_LORA_ENABLE_DUAL_STREAM=False"
            )
            envs.VLLM_LORA_ENABLE_DUAL_STREAM = False
        return self

    def verify_with_model_config(self, model_config: ModelConfig):
        if self.lora_dtype in (None, "auto"):
            self.lora_dtype = model_config.dtype
        elif isinstance(self.lora_dtype, str):
            self.lora_dtype = getattr(torch, self.lora_dtype)

        architectures = getattr(model_config, "architectures", None) or []
        is_inkling = any("Inkling" in arch for arch in architectures)
        if is_inkling and os.environ.get("INKLING_MULTIMEM_AR", "1") != "0":
            raise ValueError(

View on GitHub (pinned to c794754062)

Solutions

  1. Disable dual CUDA streams on non-CUDA platforms, or run on a CUDA platform.

When it happens

Trigger: Raised at vllm/config/lora.py:126 when validation fails: Dual CUDA streams are only supported on CUDA platforms.. 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/lora.py:126 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/57b8cf1af98e2084. Report an issue: GitHub.