sgl-project/sglang · error · ValueError

target.short_edge must be an integer, got {value!r}

Error message

target.short_edge must be an integer, got {value!r}

What it means

base_short_edge passed to minimax_h3_resolve_spatial_shape must be convertible to int. This error fires when float()/int() conversion raises TypeError (None) or ValueError (non-numeric string) inside _validate_base_short_edge.

Source

Thrown at python/sglang/multimodal_gen/runtime/pipelines_core/stages/model_specific_stages/minimax_h3/resolved_plan.py:104

        raise ValueError(
            f"target.aspect_ratio must be integer 'W:H', got {value!r}"
        ) from exc
    if w <= 0 or h <= 0:
        raise ValueError(
            f"target.aspect_ratio components must be positive, got {value!r}"
        )
    return w, h


def _nearest_multiple(value: float, multiple: int) -> int:
    return max(multiple, int(round(float(value) / multiple)) * multiple)


def _validate_base_short_edge(value: Any) -> int:
    try:
        short_edge = int(value)
    except (TypeError, ValueError) as exc:
        raise ValueError(
            f"target.short_edge must be an integer, got {value!r}"
        ) from exc
    if short_edge != value or short_edge <= 0:
        raise ValueError(f"target.short_edge must be a positive integer, got {value!r}")
    if short_edge != MINIMAX_H3_BASE_SHORT_EDGE:
        warn_unverified_short_edge(short_edge)
    return short_edge


def minimax_h3_resolve_spatial_shape(
    *,
    width: int | float,
    height: int | float,
    base_short_edge: int = MINIMAX_H3_BASE_SHORT_EDGE,
) -> dict[str, Any]:
    """Resolve one display ratio with the ``adapt_shape_v1`` math.

    This is the only implementation of adaptive target geometry. Callers may

View on GitHub (pinned to 0132848349)

Solutions

1. Pass an integer base short edge (nominally MINIMAX_H3_BASE_SHORT_EDGE)
2. Coerce or default the value at the config boundary before calling the resolver

Example fix

# before
resolve_spatial_shape(base_short_edge=config.short_edge)  # None
# after
resolve_spatial_shape(base_short_edge=config.short_edge or MINIMAX_H3_BASE_SHORT_EDGE)

def edge_ok(v):
    try: return int(v) == v and int(v) > 0
    except (TypeError, ValueError): return False

def is_valid_short_edge(v) -> bool:
    try: return type(int(v)) is int and int(v) == v and int(v) > 0
    except (TypeError, ValueError): return False

null

When it happens

Trigger: Calling minimax_h3_resolve_spatial_shape with base_short_edge=None, 'large', or another non-numeric value.

Common situations: Forwarding an unvalidated config field or JSON value straight into the resolver; optional CLI arg defaulting to None when omitted.

Related errors

• target.short_edge must be a positive integer, got {value!r}
• shape width and height must be positive finite numbers
• {path}.short_edge must be positive, got {short_edge}
• shape ratio must be a positive finite number
• adapt_shape_v1 ratio must be within the inclusive range 1:4

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/0d2bf6fcaea8c124. Report an issue: GitHub.