Commit History

Auteur SHA1 Bericht Datum
  Jeffrey Morgan 80ee9b5e47 Remove out of space test temporarily (#5825) 9 maanden geleden
  Daniel Hiltgen 06e5d74e34 Merge pull request #5506 from dhiltgen/sched_tests 9 maanden geleden
  royjhan b9f5e16c80 Introduce `/api/embed` endpoint supporting batch embedding (#5127) 9 maanden geleden
  Daniel Hiltgen f4408219e9 Refine scheduler unit tests for reliability 10 maanden geleden
  Daniel Hiltgen af28b94533 Merge pull request #5469 from dhiltgen/prevent_system_oom 10 maanden geleden
  Daniel Hiltgen 955f2a4e03 Only set default keep_alive on initial model load 10 maanden geleden
  Daniel Hiltgen 3c75113e37 Prevent loading models larger than total memory 10 maanden geleden
  Daniel Hiltgen 3518aaef33 Merge pull request #4218 from dhiltgen/auto_parallel 10 maanden geleden
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 maanden geleden
  Daniel Hiltgen 17b7186cd7 Enable concurrency by default 1 jaar geleden
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental 10 maanden geleden
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 maanden geleden
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 maanden geleden
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 maanden geleden
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) 10 maanden geleden
  Michael Yang e40145a39d lint 11 maanden geleden
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 maanden geleden
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 maanden geleden
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 11 maanden geleden
  Daniel Hiltgen 0a954e5066 Fix stale test logic 1 jaar geleden
  Jeffrey Morgan dfa2f32ca0 unload in critical section (#4187) 1 jaar geleden
  Daniel Hiltgen f56aa20014 Centralize server config handling 1 jaar geleden
  Daniel Hiltgen 9a32c514cb Soften timeouts on sched unit tests 1 jaar geleden
  Daniel Hiltgen d6e3b64582 Fix concurrency for CPU mode 1 jaar geleden
  Jeffrey Morgan 00b0699c75 Reload model if `num_gpu` changes (#3920) 1 jaar geleden
  Bryce Reitano 36a6daccab Restructure loading conditional chain 1 jaar geleden
  Bryce Reitano ceb0e26e5e Provide variable ggml for TestLoad 1 jaar geleden
  Bryce Reitano 284e02bed0 Move ggml loading to when we attempt fitting 1 jaar geleden
  Daniel Hiltgen d8851cb7a0 Harden sched TestLoad 1 jaar geleden
  Daniel Hiltgen 34b9db5afc Request and model concurrency 1 jaar geleden