sgl-project/sglang · error · TimeoutError

Video generation timed out after {max_wait_time} seconds

Error message

Video generation timed out after {max_wait_time} seconds

What it means

TimeoutError raised by generate_video when the polling loop exceeds max_wait_time seconds without the job reaching a completed/failed state. The job may still be running server-side; only the client stopped waiting.

Source

Thrown at python/sglang/multimodal_gen/apps/ComfyUI_SGLDiffusion/core/server_api.py:354

                except requests.exceptions.ConnectionError as e:
                    # Connection errors - likely server is down
                    consecutive_errors += 1
                    if consecutive_errors >= max_consecutive_errors:
                        raise RuntimeError(
                            f"Lost connection to server after {consecutive_errors} consecutive errors. "
                            f"Server may be unavailable: {str(e)}"
                        )
                except requests.exceptions.RequestException as e:
                    # Other network errors - continue polling but track errors
                    consecutive_errors += 1
                    if consecutive_errors >= max_consecutive_errors:
                        raise RuntimeError(
                            f"Network error after {consecutive_errors} consecutive failures: {str(e)}"
                        )

                time.sleep(poll_interval)

            raise TimeoutError(
                f"Video generation timed out after {max_wait_time} seconds"
            )
        except requests.exceptions.RequestException as e:
            raise RuntimeError(f"Failed to generate video: {str(e)}")

    def _build_image_common_params(
        self,
        prompt: str,
        size: str,
        n: int,
        response_format: str,
        negative_prompt: Optional[str] = None,
        guidance_scale: Optional[float] = None,
        num_inference_steps: Optional[int] = None,
        seed: Optional[int] = None,
        enable_teacache: bool = False,
        background: Optional[str] = None,
        output_format: Optional[str] = None,

View on GitHub (pinned to 0132848349)

Solutions

1. Pass a larger max_wait_time to generate_video for long jobs.
2. Reduce the job cost: smaller size, fewer seconds, lower fps.
3. Check the server queue to ensure the job is actually progressing rather than stuck.
4. Note the job ID from logs and poll manually / retry if the server supports job resubmission.

Example fix

// before
result = api.generate_video(prompt=p, seconds=10)  # timed out after max_wait_time
// after
result = api.generate_video(prompt=p, seconds=10, max_wait_time=3600, poll_interval=10)

estimated = seconds * (width * height) / 2_000_000 * 60
max_wait = max(600, int(estimated * 3))  # budget before submitting

try:
    return api.generate_video(prompt=p, max_wait_time=3600)
except TimeoutError:
    poll_job_status_manually(job_id)  # job may still complete server-side

When it happens

Trigger: Long video generations (high resolution, many seconds, slow hardware) that exceed the default max_wait_time; a stuck/queued job behind other work on the server.

Common situations: Default wait budget too small for 4K/multi-second videos; queued jobs waiting for GPU availability; server heavily loaded so each step is slow.

Understand the failure class

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• Network error after {consecutive_errors} consecutive failure
• Video generation failed: {error_msg}
• Lost connection to server after {consecutive_errors} consecu
• Failed to edit image: {str(e)}
• Failed to generate image: {str(e)}

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/e39a2cb18bdc91d0. Report an issue: GitHub.