Support for VPU-based video infrastructure—designed for real deployments, not experiments.
Contact support for deployment assistance.
View and manage active support tickets
Firmware, drivers, and VPU software releases.
Technical guides,
SDKs, and APIs.
Known issues, causes, and what to check first.
Most likely causes: Initialization, BIOS, or driver alignment.
Check:
Rule: If the OS doesn’t see the card, the application won’t either.
Most likely causes: System configuration, not hardware limits.
Check:
Rule: VPUs deliver predictable performance when the surrounding system is tuned correctly.
Most likely causes: Power, thermal, or system-level constraints.
Check:
Rule: High density requires balanced systems—not just more cards.
Most likely risks: Version incompatibility and uncontrolled rollout.
Check:
Rule: Treat updates like infrastructure changes, not patches.
Most likely causes: Input irregularities or resource exhaustion.
Check:
Rule: Intermittent failures usually originate upstream of the VPU.
Most likely failure mode: Scaling too fast without validation.
Check:
Rule: Scale incrementally and validate at each step.
Ownership follows the architecture.
Check:
Rule: Escalate based on root cause, not symptoms.
Most likely causes: Infrastructure asymmetry.
Check:
Rule: Hybrid performance must be evaluated per environment.
Most likely causes: Assumptions of uniform infrastructure.
Check:
Rule: Hybrid orchestration requires environment-specific tuning.
Most common hybrid failure mode: Inconsistent firmware, drivers, or SDKs.
Check:
Rule: Control upgrades centrally and apply incrementally.
