vllm-project/vllm · error · ValueError

Unknown Mamba SSU backend: '{name}'. Valid options are: {val

Error message

Unknown Mamba SSU backend: '{name}'. Valid options are: {valid}

What it means

Error "Unknown Mamba SSU backend: '{name}'. Valid options are: {valid}" thrown in vllm-project/vllm.

Source

Thrown at vllm/config/mamba.py:20

# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

from enum import Enum, EnumMeta
from typing import Any, Literal, get_args

from pydantic import field_validator

from vllm.config.utils import config


class _MambaBackendEnumMeta(EnumMeta):
    """Metaclass for MambaBackendEnum to provide better error messages."""

    def __getitem__(cls, name: str):
        try:
            return super().__getitem__(name)
        except KeyError:
            valid = ", ".join(cls.__members__.keys())
            raise ValueError(
                f"Unknown Mamba SSU backend: '{name}'. Valid options are: {valid}"
            ) from None


class MambaBackendEnum(Enum, metaclass=_MambaBackendEnumMeta):
    """Enumeration of supported Mamba SSU (selective state update) backends."""

    TRITON = "triton"
    FLASHINFER = "flashinfer"
    CPU = "cpu"


MambaSSUAlgorithm = Literal["auto", "simple", "vertical", "horizontal"]


@config
class MambaConfig:
    """Configuration for Mamba SSM backends."""

View on GitHub (pinned to c794754062)

Solutions

1. Choose one of the valid Mamba SSU backends listed in the error for --mamba-backend.

When it happens

Trigger: Raised at vllm/config/mamba.py:20 when validation fails: Unknown Mamba SSU backend. 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/mamba.py:20 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/bd0d31a73e76bfd0. Report an issue: GitHub.