Unverified50% confidenceFactExact time
ExecuTorch is an on-device inference runtime framework launched by Meta, built on the Export mechanism of PyTorch 2.0.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe ExecuTorch workflow consists of three phases: exporting the model computation graph with torch.export, performing quantization and optimization through compiler passes, and finally packaging into the .pte format to run on the target device.71% similarUnverifiedBy feeding the structured output of Explorer into an agentic flow, an LLM or rule engine can be used to automatically interpret trace data, identify bottlenecks, and generate optimization recommendations.63% similarUnverifiedExcalidraw is an open-source whiteboard tool known for its hand-drawn style, simple interaction, and local-first data handling.60% similarUnverifiedCliRelay的核心技术实现是进程代理（Process Proxy）模式，通过Go的os/exec包创建子进程来包装命令行工具59% similarUnverified推理链路通过ONNX Runtime承载，后端使用Intel OpenVINO作为执行provider，并开启多设备模式和延迟优先提示58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989421API
curl https://kongchang.com/api/v1/knowledge/claims/989421MCP
get_claim(id=989421)