vllm-project/vllm · error · Error

`{modality}` input is not supported by this model

Error message

`{modality}` input is not supported by this model

What it means

The NixlEplbCommunicator constructor raised {exc}; the factory wraps and chains it. The underlying failure is usually inside agent creation, descriptor registration, or an assertion on empty weights/buffers (the constructor asserts non-empty all_expert_weights and expert_buffer).

Source

Thrown at rust/src/chat/src/error.rs:24

type BoxedError = Box<dyn std::error::Error + Send + Sync>;

#[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,

View on GitHub (pinned to c794754062)

Solutions

1. Check the chained exception text for the specific failing step — the factory re-raises the original cause
2. Confirm all_expert_weights and expert_buffer are non-empty and on the correct device
3. If the cause is a _init_step failure, follow the fixes for error 464 (UCX/NIXL environment)

assert all_expert_weights and expert_weights, 'NixlEplbCommunicator requires non-empty weights and buffer'

try:
    comm = NixlEplbCommunicator(...)
except RuntimeError as e:
    if 'Failed to initialize NixlEplbCommunicator' in str(e):
        log.error('cause: %r', e.__cause__)
    raise

When it happens

Trigger: Passing empty all_expert_weights or expert_buffer; a NIXL agent/descriptor error from _init_step (see error 464) bubbling through the factory; invalid cpu_group for collective metadata exchange.

Common situations: Initializing EPLB before the model's expert weights are populated; fabric/UCX problems during agent creation; elastic ranks constructing the communicator with different world sizes.

Related errors

• Configuration error: {0}
• Endpoint not ready after {0}s: {1}
• Backend error: {0}
• IO error: {0}
• chat template is required but none was configured

AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14). Data as JSON: /api/errors/4476123db632da3d. Report an issue: GitHub.