sgl-project/sglang · error · ValueError

cannot parse boolean batching config value: {value!r}

Error message

cannot parse boolean batching config value: {value!r}

What it means

Boolean-typed optional fields in a rule accept bools and the strings 1/true/yes/y/on and 0/false/no/n/off (case-insensitive). _optional_bool raises when the value is any other string or an unparseable type.

Source

Thrown at python/sglang/multimodal_gen/runtime/managers/dynamic_batch_admission.py:349

def _optional_float(value: Any) -> float | None:
    if value is None:
        return None
    return float(value)


def _optional_bool(value: Any) -> bool | None:
    if value is None:
        return None
    if isinstance(value, bool):
        return value
    if isinstance(value, str):
        lowered = value.strip().lower()
        if lowered in ("1", "true", "yes", "y", "on"):
            return True
        if lowered in ("0", "false", "no", "n", "off"):
            return False
    raise ValueError(f"cannot parse boolean batching config value: {value!r}")

View on GitHub (pinned to 0132848349)

Solutions

1. Use a real JSON boolean true/false
2. If a string is required, use one of: 1/true/yes/y/on or 0/false/no/n/off

Example fix

// before
{"model": "x", "max_batch_size": 4, "some_flag": "enabled"}
// after
{"model": "x", "max_batch_size": 4, "some_flag": true}

BOOL_STR = {"1","true","yes","y","on","0","false","no","n","off"}
def ok_bool(v):
    return isinstance(v, bool) or (isinstance(v, str) and v.strip().lower() in BOOL_STR)

def is_parseable_bool(v) -> bool:
    return isinstance(v, bool) or (isinstance(v, str) and v.strip().lower() in {"1","true","yes","y","on","0","false","no","n","off"})

When it happens

Trigger: A rule field parsed via _optional_bool with a value like "enabled", "maybe", or an int like 2 (non-bool, non-recognized string).

Common situations: Config generated from YAML where booleans were quoted arbitrarily; env-var-style values like "TRUE " handled fine but custom words like "enable" are not.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

• batching config rule requires max_batch_size
• batching config rule cannot set both model and model_contain
• batching config rule requires model or model_contains
• batching config rule max_batch_size must be >= 1
• batching config rule max_cost must be > 0

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/0490ed10da6500c0. Report an issue: GitHub.