keras-team/keras · error · ValueError
Unsupported arguments for LiteRT export with the PyTorch bac
Error message
Unsupported arguments for LiteRT export with the PyTorch backend: {', '.join(unsupported_args)}. Supported arguments are: {', '.join(supported_args)}. What it means
Error "Unsupported arguments for LiteRT export with the PyTorch backend: {', '.join(unsupported_args)}. Supported arguments are: {', '.join(supported_args)}." thrown in keras-team/keras.
Source
Thrown at keras/src/export/litert.py:288
for k, v in kwargs.items():
if k in valid_litert_torch_args:
litert_torch_kwargs[k] = v
if "optimizations" in kwargs and "quant_config" not in litert_torch_kwargs:
quant_cfg = _create_quant_config_from_optimizations(
kwargs["optimizations"], litert_torch
)
if quant_cfg is not None:
litert_torch_kwargs["quant_config"] = quant_cfg
unsupported_args = sorted(
key
for key in kwargs
if key not in valid_litert_torch_args and key != "optimizations"
)
if unsupported_args:
supported_args = sorted(valid_litert_torch_args | {"optimizations"})
raise ValueError(
"Unsupported arguments for LiteRT export with the PyTorch "
f"backend: {', '.join(unsupported_args)}. Supported arguments "
f"are: {', '.join(supported_args)}."
)
return litert_torch_kwargs
def _get_litert_torch_kwarg_names(litert_torch):
return {
name
for name in inspect.signature(litert_torch.convert).parameters
if name not in {"module", "sample_args", "sample_kwargs"}
}
@contextlib.contextmanager
def _preserve_jax_x64_state():View on GitHub (pinned to 7a34a03db6)
When it happens
Trigger: Thrown at keras/src/export/litert.py:288 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25).
Data as JSON: /api/errors/410f0f79f72d09a7.
Report an issue: GitHub.