Fine-grained sharing and isolation
Declare GPU memory, compute and device requirements. Run multiple tasks on supported devices, configure resource limits and monitor usage.
Device-dependent supportBuilt on open-source HAMi, add GPU sharing, scheduling and runtime enhancements to Kubernetes, PaaS and AI platforms while keeping your existing workflows.
Enhance your existing platform’s resource management, from sharing efficiency to runtime policies.
Declare GPU memory, compute and device requirements. Run multiple tasks on supported devices, configure resource limits and monitor usage.
Device-dependent supportOrganize accelerators from different vendors and models into unified resource pools, then allocate and schedule by workload demand to simplify heterogeneous resource management.
Enterprise capabilityUse Binpack / Spread at node and device level, plus device type, UUID and topology to control workload placement.
Device and version dependentWith UMI, idle GPU memory can be swapped back to host memory so more concurrent workloads fit beyond physical VRAM—suited to tidal colocation.
NVIDIA · Model and version dependentAdjust GPU memory quotas from real load; when a workload would otherwise OOM, raise the limit automatically without restarting the container.
NVIDIA · Model and version dependentCompute calls go straight to the CUDA Runtime—no compute hijacking. Keep only essential monitoring while VRAM limits still apply; built for low-latency workloads.
NVIDIA · Model and version dependentCreate and remove MIG instances from predefined templates. Users declare count and memory only—MIG instance names stay transparent.
NVIDIA · Model and version dependentCreate and reclaim vNPU instances from predefined templates. Users declare count and memory only—no need to know template names.
Subject to hardware and compatibility matrixWhen a high-priority workload uses GPU compute, lower-priority workloads are paused and resume after it finishes—protecting critical capacity.
NVIDIA · version dependentKubernetes resource requests pass through admission, device selection and injection to place workloads on target GPUs. The runtime enforces supported GPU memory and compute limits.
Online and offline deployment, tailored to your infrastructure.
Verify chip model, driver, runtime, and Kubernetes version.
Accept based on throughput, latency, stability, and resource usage.
Define installation, upgrades, monitoring, and offline delivery.
Choose Dynamia Enterprise for HAMi to integrate virtualization and scheduling into your platform. If you also need unified multi-cluster, tenant and billing management, evaluate AI Platform.
No. GPU memory oversubscription, elastic GPU memory expansion, Turbo and workload priority depend on the NVIDIA model and product version. Dynamic MIG and Dynamic NPU also have specific hardware requirements.
Tell us about your devices, clusters and business goals to identify the right product, deployment approach and validation path.