vllm-project/vllm · error · Error

At most {limit} {modality}(s) may be provided in one prompt.

Error message

At most {limit} {modality}(s) may be provided in one prompt.

What it means

The EPLB communicator factory reached the end of its dispatch chain without matching the backend string. Recognized values are 'nixl', 'torch_gloo', 'torch_nccl', and 'pynccl'; anything else (including typos) raises this ValueError.

Source

Thrown at rust/src/chat/src/error.rs:26

#[derive(Debug, Error, Macro)]
#[thiserror_ext(macro(path = "crate::error"))]
pub enum Error {
    #[error("chat request must contain at least one message")]
    EmptyMessages,
    #[error("cannot continue the final message when the last message is not from the assistant")]
    ContinueFinalAssistantWithoutFinalAssistant,
    #[error("chat template is required but none was configured")]
    MissingChatTemplate,
    #[error("chat template error: {0}")]
    ChatTemplate(String),
    #[error("multimodal input is not supported by this chat renderer")]
    UnsupportedMultimodalRenderer,
    #[error("unsupported multimodal content: {0}")]
    UnsupportedMultimodalContent(&'static str),
    #[error("`{modality}` input is not supported by this model")]
    UnsupportedModality { modality: String },
    #[error("At most {limit} {modality}(s) may be provided in one prompt.")]
    MmLimitExceeded { modality: String, limit: usize },
    #[error("multimodal preprocessing error: {0}")]
    Multimodal(#[message] String),
    #[error("{kind} parsing is not available for model `{model_id}`")]
    ParserUnavailableForModel {
        kind: &'static str,
        model_id: String,
    },
    #[error("{kind} parsing is disabled by frontend configuration")]
    ParserDisabled { kind: &'static str },
    #[error(
        "{kind} parser `{name}` is not registered{}",
        available_parser_hint(.available_names)
    )]
    ParserUnavailableByName {
        kind: &'static str,
        name: String,
        available_names: Vec<String>,

View on GitHub (pinned to c794754062)

Solutions

1. Use one of: 'nixl', 'torch_gloo', 'torch_nccl', 'pynccl' (exact lowercase)
2. Validate/normalize the backend string at config load time instead of deep in the factory

Example fix

# before
backend = "nccl"

# after
backend = "torch_nccl"

VALID_EPLB_BACKENDS = {'nixl', 'torch_gloo', 'torch_nccl', 'pynccl'}
assert backend in VALID_EPLB_BACKENDS, f'backend must be one of {VALID_EPLB_BACKENDS}'

def is_valid_eplb_backend(backend: str) -> bool:
    return backend in ('nixl', 'torch_gloo', 'torch_nccl', 'pynccl')

When it happens

Trigger: Calling the factory with an arbitrary or misspelled backend string, e.g. 'gloo', 'nccl', or 'NIXL' (case-sensitive).

Common situations: User-supplied config strings; case mismatches; backends removed or renamed across vLLM versions.

Related errors

• chat template error: {0}
• multimodal input is not supported by this chat renderer
• Configuration error: {0}
• Endpoint not ready after {0}s: {1}
• Backend error: {0}

AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14). Data as JSON: /api/errors/70f9ff0285216b90. Report an issue: GitHub.