提交歷史

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