vllm-project/vllm · error · ValueError

manager_config requires encoder_cache_manager_cls to be set.

Error message

manager_config requires encoder_cache_manager_cls to be set.

What it means

Error "manager_config requires encoder_cache_manager_cls to be set." thrown in vllm-project/vllm.

Source

Thrown at vllm/config/ec_manager_config.py:22

from abc import ABC
from dataclasses import field
from typing import Any

from vllm.config.utils import config
from vllm.utils.import_utils import resolve_obj_by_qualname


@config
class EncoderCacheManagerConfig:
    encoder_cache_manager_cls: str | None = None
    """Fully qualified class name of the custom encoder cache manager."""

    manager_config: dict[str, Any] = field(default_factory=dict)
    """Opaque configuration interpreted by the custom cache manager."""

    def __post_init__(self) -> None:
        if self.encoder_cache_manager_cls is None and self.manager_config:
            raise ValueError(
                "manager_config requires encoder_cache_manager_cls to be set."
            )

    def get_encoder_cache_manager_obj(self):
        cls_path = self.encoder_cache_manager_cls
        if cls_path is None:
            return None
        return resolve_obj_by_qualname(cls_path)


class EncoderCacheManagerMetadata(ABC):  # noqa: B024
    """
    Abstract Metadata used to communicate between the
    Scheduler EncoderCacheManager and Worker EncoderCacheManager.
    """

    pass

View on GitHub (pinned to c794754062)

Solutions

1. Set encoder_cache_manager_cls in the manager_config before use.

When it happens

Trigger: Raised at vllm/config/ec_manager_config.py:22 when validation fails: manager_config requires encoder_cache_manager_cls to be set.. 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/ec_manager_config.py:22 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/1bc4ea81d3cf370b. Report an issue: GitHub.