Revīziju vēsture

Autors SHA1 Ziņojums Datums
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 mēneši atpakaļ
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental 10 mēneši atpakaļ
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 mēneši atpakaļ
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 mēneši atpakaļ
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 mēneši atpakaļ
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) 10 mēneši atpakaļ
  Michael Yang e40145a39d lint 11 mēneši atpakaļ
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 mēneši atpakaļ
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 mēneši atpakaļ
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 11 mēneši atpakaļ
  Daniel Hiltgen 0a954e5066 Fix stale test logic 1 gadu atpakaļ
  Jeffrey Morgan dfa2f32ca0 unload in critical section (#4187) 1 gadu atpakaļ
  Daniel Hiltgen f56aa20014 Centralize server config handling 1 gadu atpakaļ
  Daniel Hiltgen 9a32c514cb Soften timeouts on sched unit tests 1 gadu atpakaļ
  Daniel Hiltgen d6e3b64582 Fix concurrency for CPU mode 1 gadu atpakaļ
  Jeffrey Morgan 00b0699c75 Reload model if `num_gpu` changes (#3920) 1 gadu atpakaļ
  Bryce Reitano 36a6daccab Restructure loading conditional chain 1 gadu atpakaļ
  Bryce Reitano ceb0e26e5e Provide variable ggml for TestLoad 1 gadu atpakaļ
  Bryce Reitano 284e02bed0 Move ggml loading to when we attempt fitting 1 gadu atpakaļ
  Daniel Hiltgen d8851cb7a0 Harden sched TestLoad 1 gadu atpakaļ
  Daniel Hiltgen 34b9db5afc Request and model concurrency 1 gadu atpakaļ