História revízii

Autor SHA1 Správa Dátum
  Daniel Hiltgen 9bceb3b55e Enable concurrency by default 1 rok pred
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 mesiacov pred
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental 10 mesiacov pred
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 mesiacov pred
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 mesiacov pred
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 mesiacov pred
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) 10 mesiacov pred
  Michael Yang e40145a39d lint 11 mesiacov pred
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 mesiacov pred
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 mesiacov pred
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 11 mesiacov pred
  Daniel Hiltgen 0a954e5066 Fix stale test logic 1 rok pred
  Jeffrey Morgan dfa2f32ca0 unload in critical section (#4187) 1 rok pred
  Daniel Hiltgen f56aa20014 Centralize server config handling 1 rok pred
  Daniel Hiltgen 9a32c514cb Soften timeouts on sched unit tests 1 rok pred
  Daniel Hiltgen d6e3b64582 Fix concurrency for CPU mode 1 rok pred
  Jeffrey Morgan 00b0699c75 Reload model if `num_gpu` changes (#3920) 1 rok pred
  Bryce Reitano 36a6daccab Restructure loading conditional chain 1 rok pred
  Bryce Reitano ceb0e26e5e Provide variable ggml for TestLoad 1 rok pred
  Bryce Reitano 284e02bed0 Move ggml loading to when we attempt fitting 1 rok pred
  Daniel Hiltgen d8851cb7a0 Harden sched TestLoad 1 rok pred
  Daniel Hiltgen 34b9db5afc Request and model concurrency 1 rok pred