vllm-project/vllm · error · ValueError

max_cpu_loras ({self.max_cpu_loras}) must be >= max_loras ({

Error message

max_cpu_loras ({self.max_cpu_loras}) must be >= max_loras ({self.max_loras}).

What it means

Error "max_cpu_loras ({self.max_cpu_loras}) must be >= max_loras ({self.max_loras})." thrown in vllm-project/vllm.

Source

Thrown at vllm/config/lora.py:121

        factors.append(self.fully_sharded_loras)
        factors.append(self.lora_dtype)
        factors.append(self.enable_tower_connector_lora)
        factors.append(self.enable_mixed_moe_lora_format)
        factors.append(self.enable_moe_shared_loras)
        # 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)

View on GitHub (pinned to c794754062)

Solutions

1. Increase max_cpu_loras to be >= max_loras, or decrease max_loras.

When it happens

Trigger: Raised at vllm/config/lora.py:121 when validation fails: max_cpu_loras must be >= max_loras. 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:121 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/59e2afef434a62eb. Report an issue: GitHub.