Original link: http://gaocegege.com/Blog/ai-hype AI has recently become a hot topic again. The release of ChatGPT half a year ago shocked everyone like a bolt from the blue. But half a year has passed, and the monthly activity of ChatGPT has begun to decline. After trying many applications myself, I gradually converged on a few limited […]
Where are the barriers at the AI application layer Read More »
Original link: http://gaocegege.com/Blog/pgvectors We’ve open-sourced pgvecto.rs , a Postgres vector similarity search plugin written in Rust. Its HNSW algorithm is 20 times faster than pgvector at 90% recall. But speed is only the beginning – pgvecto.rs’ extensible architecture is designed to support new algorithms such as DiskANN. We also hope that with the help of
20x Speedup: Postgres Vector Similarity Plugin Implemented in Rust Read More »
Original link: http://gaocegege.com/Blog/modelz-beta We are pleased to announce that ModelZ , a serverless GPU inference platform, has entered Beta. Users do not need to care about the underlying infrastructure to obtain high-performance and low-cost GPU inference services. characteristic ModelZ is a hosted service that provides users with a simple API and easy-to-use UI to deploy
Serverless reasoning service ModelZ enters Beta public testing Read More »
Original link: http://gaocegege.com/Blog/vector With the popularity of LLM, the vector database has also become a hot topic. With just a few simple Python codes, the vector database can plug in a cheap but extremely effective “external brain” for your LLM. But do we really need a (specialized) vector database? Why does LLM need vector search?
Do you really need a (specialized) vector database Read More »
Original link: http://gaocegege.com/Blog/kubernetes/metrics-survey TL; DR In order to better support the collection of training metrics and the performance profiling of tasks, we designed a small-scale survey of machine learning development observability. envd Support profiler that is more in line with the needs of algorithm engineers Function. Welcome to participate! Deep learning training is rare and
How to perform performance tuning for deep learning training? Read More »
Original link: http://gaocegege.com/Blog/kubernetes/tensorchord-tea-hour-1 Buildkit is the backbone behind docker build , when we are using When docker builds an image, the credit behind it is buildkit. So everyone is probably a user of Buildkit, although most of its brilliance has been hidden by docker. tensorchord/envd It is also implemented based on buildkit, for algorithm engineers
TensorChord Tea Hour Technology Sharing: Buildkit Internals Read More »