sgl-project/sglang · error · ValueError

{path}.short_edge must be positive, got {short_edge}

Error message

{path}.short_edge must be positive, got {short_edge}

What it means

Raised by the MiniMax-H3 canonical request validator when target.short_edge is an integer <= 0. short_edge controls the shorter output dimension and must be a positive int; the recommended value is MINIMAX_H3_RECOMMENDED_SHORT_EDGE, which also suppresses an 'unverified configuration' warning.

Source

Thrown at python/sglang/multimodal_gen/runtime/pipelines_core/stages/model_specific_stages/minimax_h3/request_validation.py:89

        return None
    if isinstance(value, bool) or not isinstance(value, (int, float)):
        raise ValueError(f"{path} must be a number")
    normalized = float(value)
    if not math.isfinite(normalized) or normalized < 0.0:
        raise ValueError(f"{path} must be a non-negative finite number")
    return normalized


def _validate_target(target: Any, *, profile: MiniMaxH3TaskProfile) -> dict[str, Any]:
    path = "target"
    if not isinstance(target, Mapping):
        raise ValueError(f"{path} is required and must be an object")
    # The canonical target has a deliberately small projection.  Transport
    # compatibility keys are ignored; only these three declared values are
    # validated and emitted below.
    short_edge = _require_int(target.get("short_edge"), f"{path}.short_edge")
    if short_edge <= 0:
        raise ValueError(f"{path}.short_edge must be positive, got {short_edge}")
    if short_edge != MINIMAX_H3_RECOMMENDED_SHORT_EDGE:
        # Same guard the resolver applies. Without it the recommended value warns
        # that it is "outside the verified configuration", naming itself as the
        # verified one.
        warn_unverified_short_edge(short_edge)
    aspect_ratio = _require_str(target.get("aspect_ratio"), f"{path}.aspect_ratio")
    if profile.aspect_ratio_forced_auto and aspect_ratio != "auto":
        raise ValueError(
            f'{path}.aspect_ratio must be "auto" for task {profile.task!r}, '
            f"got {aspect_ratio!r}"
        )
    has_duration = target.get("duration_seconds") is not None
    if (
        profile.task in {MINIMAX_H3_TASK_T2VA, MINIMAX_H3_TASK_REF2VA}
        and aspect_ratio != "auto"
        and aspect_ratio not in MINIMAX_H3_FINITE_ASPECT_RATIOS
    ):
        raise ValueError(

View on GitHub (pinned to 0132848349)

Solutions

1. Set short_edge to MINIMAX_H3_RECOMMENDED_SHORT_EDGE (the verified default)
2. Ensure any computed short_edge is clamped to >= 1 before submission
3. Audit config templates for 0/None placeholders that reach the validator

Example fix

// before
{"target": {"short_edge": 0, "aspect_ratio": "auto"}}
// after
{"target": {"short_edge": 768, "aspect_ratio": "auto"}}

if not isinstance(target['short_edge'], int) or target['short_edge'] <= 0:
    raise ValueError('short_edge must be a positive integer')

def is_valid_short_edge(v) -> bool:
    return isinstance(v, int) and not isinstance(v, bool) and v > 0

When it happens

Trigger: Calling minimax_h3_validate_canonical_request with a target dict where short_edge is 0 or negative (e.g. copied from a placeholder or computed from a subtraction that underflowed).

Common situations: Defaulting short_edge to 0 in a config template; computing it as height - crop where crop > height; passing a bool (False == 0) after _require_int accepted it via bool-int equivalence.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• MiniMax-H3 adaln_t_table must have shape [N, D] with N >= 2,
• MiniMax H3 AdaLN cache has invalid timestep plans
• TP size must be positive.
• num_attention_heads must be positive.
• hidden_size must be positive.

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/e769bc6ab6516095. Report an issue: GitHub.