Commit History

Autor SHA1 Mensaxe Data
  ManniX-ITA bd54b08261 Streamlined WaitUntilRunning hai 1 ano
  Michael Yang 26df674785 scale graph based on gpu count hai 1 ano
  Michael Yang 41a272de9f darwin: no partial offloading if required memory greater than system hai 1 ano
  Jeffrey Morgan a0b8a32eb4 Terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading (#3653) hai 1 ano
  Michael Yang 7e33a017c0 partial offloading hai 1 ano
  Michael Yang 8b2c10061c refactor tensor query hai 1 ano
  Daniel Hiltgen c5ff443b9f Handle very slow model loads hai 1 ano
  Michael Yang be517e491c no rope parameters hai 1 ano
  Michael Yang 12e923e158 update graph size estimate hai 1 ano
  Daniel Hiltgen 464d817824 Merge pull request #3464 from dhiltgen/subprocess hai 1 ano
  Daniel Hiltgen 6589eb8a8c Revert options as a ref in the server hai 1 ano
  Michael Yang 80163ebcb5 fix metal gpu hai 1 ano
  Daniel Hiltgen 58d95cc9bd Switch back to subprocessing for llama.cpp hai 1 ano