sgl-project/sglang · error · ValueError

missing `sample` as a required keyword argument

Error message

missing `sample` as a required keyword argument

What it means

convert_model_output requires the noisy sample tensor; the legacy signature allows positional args, but if `sample` was not passed as the second positional arg or as a keyword, there is nothing to convert and it raises. `timestep` is likewise deprecated because step indexing is internal now.

Source

Thrown at python/sglang/multimodal_gen/runtime/models/schedulers/scheduling_unipc_multistep.py:734

        Args:
            model_output (`torch.Tensor`):
                The direct output from the learned diffusion model.
            timestep (`int`):
                The current discrete timestep in the diffusion chain.
            sample (`torch.Tensor`):
                A current instance of a sample created by the diffusion process.

        Returns:
            `torch.Tensor`:
                The converted model output.
        """
        timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
        if sample is None:
            if len(args) > 1:
                sample = args[1]
            else:
                raise ValueError("missing `sample` as a required keyword argument")
        if timestep is not None:
            deprecate(
                "timesteps",
                "1.0.0",
                "Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        sigma = self.sigmas[self.step_index]
        alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)

        if self.predict_x0:
            if self.config.prediction_type == "epsilon":
                x0_pred = (sample - sigma_t * model_output) / alpha_t
            elif self.config.prediction_type == "sample":
                x0_pred = model_output
            elif self.config.prediction_type == "v_prediction":
                x0_pred = alpha_t * sample - sigma_t * model_output
            elif self.config.prediction_type == "flow_prediction":

View on GitHub (pinned to 0132848349)

Solutions

1. Call scheduler.step(model_output, timestep, sample) instead of convert_model_output directly
2. If calling convert_model_output, pass sample explicitly: convert_model_output(model_output, sample=sample)
3. Do not pass timestep — it is deprecated and ignored

Example fix

// before
x0 = sched.convert_model_output(model_output)
// after
x0 = sched.convert_model_output(model_output, sample=sample)
# or preferably
out = sched.step(model_output, t, sample)

assert sample is not None, "sample tensor is required"

When it happens

Trigger: Calling scheduler.convert_model_output(model_output) with no `sample` positional/keyword, e.g. porting old code that passed only (model_output, sample) order incorrectly or omitted sample.

Common situations: User code calling scheduler internals directly instead of scheduler.step(); upgrading from old diffusers versions where the call signature differed.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• missing `order` as a required keyword argument
• missing `last_sample` as a required keyword argument
• missing `this_sample` as a required keyword argument
• {beta_schedule} is not implemented for {self.__class__}
• {solver_type} is not implemented for {self.__class__}

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/aaf8ed2e87815603. Report an issue: GitHub.