Best of NVIDIA — 2023

1. 1
   Article

   Pointer·3y

   an open-source alternative to GitHub Copilot server

   This post discusses building a locally hosted alternative to GitHub Copilot using the SalesForce CodeGen models inside NVIDIA's Triton Inference Server with the FasterTransformer backend.

   100

   4
2. 2
   Article

   Hacker News·3y

   TabbyML/tabby: Self-hosted AI coding assistant

   TabbyML/tabby is an opensource / on-prem alternative to GitHub Copilot. Tabby is still in the alpha phase, with no need for a DBMS or cloud service. The easiest way of getting started is using the docker image: # Create data dir and grant owner to 1000 (Tabby run as uid 1000 in container).

   44
3. 3
   Article

   NVIDIA·3y

   Build AI Avatars With NVIDIA Omniverse ACE

   NVIDIA Omniverse ACE is a suite of cloud-native AI microservices that make it easier to build and deploy intelligent virtual assistants and digital humans at scale. These AI assistants can be designed for organizations across industries, enabling organizations to enhance existing workflows and unlock new business opportunities. The early-access program includes access to the prerelease versions.

   35

   2
4. 4
   Article

   freeCodeCamp·3y

   How to Setup a Windows Machine for Machine Learning/Deep Learning Using an Nvidia Graphics Card (CUDA)

   How to set up a Windows Machine for Machine Learning/Deep Learning using an Nvidia Graphics Card (CUDA) If you can afford a good Nvidia graphics card, then you can easily use your graphics card for this type of intensive work. A lot of developers use Linux for this, but I do not like Linux as a desktop operating system.

   11

   4