{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:02:01.031Z","data":{"recordId":"wsa_i7vb8db8n6ug","score":0.883,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://developers.googleblog.com/ml-drift-next-gen-gpu-aiml-inference-at-the-edge/","publisher":"Google","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-29T00:21:40.337Z","detectedPublishedAt":"2026-10-08T00:00:00.000Z","rights":"original"}],"claims":[{"id":"b80b483f-387b-4b5a-b19c-07adf92e1686","kind":"availability","statement":"ML Drift is available as a standalone library and as the GPU acceleration engine within LiteRT.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"Serving as the core GPU acceleration engine within LiteRT , ML Drift is also available as a standalone library for custom graphics and inference runtimes providing a unified foundation to deliver peak performance everywhere.","rights":"original"}}]},{"id":"6a9ca739-1632-4c55-a50c-5e34d6be3050","kind":"capability","statement":"ML Drift supports OpenGL ES, OpenCL, Metal, and WebGPU.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"By abstracting hardware and low-level API complexities of on-device GPUs across OpenGL ES, OpenCL, Metal, and WebGPU, ML Drift empowers developers to build real-time, interactive ML experiences from advanced video effects to generative AI across multiple platforms.","rights":"original"}}]},{"id":"55670c18-cccc-4d8b-abd9-193f9d50fff5","kind":"capability","statement":"ML Drift supports 5D tensors out of the box.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":null}]},{"id":"cd4c6a66-108d-49fe-a29f-272479d34e0a","kind":"deployment","statement":"ML Drift can run on Android, iOS, web, Windows, Linux, and macOS.","citations":[{"source":1,"supportProbability":0.62,"supports":false,"quote":{"text":"This unified API model enables ML Drift to run on Windows and Linux, leveraging WebGPU's modern, native hardware abstraction to bypass DirectX and Vulkan fragmentation, while complementing our existing high-performance native Metal backend on macOS.","rights":"original"}}]},{"id":"b9f03665-1b4d-4346-877b-e3b937b6e04a","kind":"capability","statement":"ML Drift dynamically switches kernels and layout configurations between LLM prefill and decode stages.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"ML Drift dynamically switches kernels and layout configurations depending on the active execution phase.","rights":"original"}}]},{"id":"3c65b3c8-dbb5-47c8-8db6-0045790cb32e","kind":"recommendation-relevant","statement":"The legacy TFLite GPU delegate will no longer receive new feature updates.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"With the launch of ML Drift, the legacy TFLite GPU delegate will no longer receive new feature updates.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}