NVIDIA Technical Blog· Dan Feigin·· 4 天前
NVIDIA Snapshot开源组件可在秒级内启动和恢复GPU工作负载
Start and Restore GPU Workloads in Seconds with NVIDIA Snapshot
要点速览
NVIDIA Snapshot 使初始化的 GPU 工作负载可跨推理副本复用，加速启动和恢复。当推理需求激增或副本故障时，可用 GPU 不会立即转化为服务能力。初始化 LLM 工作负载（冷启动）可能需要数分钟。
正文
NVIDIA Snapshot, a new open-source component of the NVIDIA DSX AI Factory Platform, makes initialized GPU workloads reusable across inference...
NVIDIA Snapshot, a new open-source component of the NVIDIA DSX AI Factory Platform, makes initialized GPU workloads reusable across inference replicas—speeding startup and recovery. When inference demand spikes or a replica fails, available GPUs don’t translate immediately into serving capacity. Initializing an LLM workload—a process known as a cold start—can take minutes…
来源: NVIDIA Technical Blog · developer.nvidia.com