Commit History

Автор SHA1 Съобщение Дата
  Michael Yang 58245413f4 next ollama runner (#7913) преди 2 месеца
  Stefan Weil abfdc4710f all: fix typos in documentation, code, and comments (#7021) преди 4 месеца
  Daniel Hiltgen 05cd82ef94 Rename gpu package discover (#7143) преди 6 месеца
  Daniel Hiltgen d632e23fba Add Windows arm64 support to official builds (#5712) преди 7 месеца
  Patrick Devine abed273de3 add "stop" command (#6739) преди 7 месеца
  Michael Yang 77903ab8b4 llama3.1 преди 9 месеца
  Jeffrey Morgan 15c2d8fe14 server: parallelize embeddings in API web handler instead of in subprocess runner (#6220) преди 8 месеца
  Michael Yang b732beba6a lint преди 9 месеца
  Michael Yang df993fa37b comments преди 9 месеца
  Michael Yang 5e9db9fb0b refactor convert преди 11 месеца
  Michael Yang 5c1912769e Merge pull request #5473 from ollama/mxyng/environ преди 9 месеца
  royjhan 1b44d873e7 Add Metrics to `api\embed` response (#5709) преди 9 месеца
  Daniel Hiltgen 345420998e Prevent partial loading on mixed GPU brands преди 9 месеца
  Michael Yang 0f1910129f int преди 10 месеца
  Jeffrey Morgan 80ee9b5e47 Remove out of space test temporarily (#5825) преди 9 месеца
  Daniel Hiltgen 06e5d74e34 Merge pull request #5506 from dhiltgen/sched_tests преди 9 месеца
  royjhan b9f5e16c80 Introduce `/api/embed` endpoint supporting batch embedding (#5127) преди 9 месеца
  Daniel Hiltgen f4408219e9 Refine scheduler unit tests for reliability преди 10 месеца
  Daniel Hiltgen af28b94533 Merge pull request #5469 from dhiltgen/prevent_system_oom преди 10 месеца
  Daniel Hiltgen 955f2a4e03 Only set default keep_alive on initial model load преди 10 месеца
  Daniel Hiltgen 3c75113e37 Prevent loading models larger than total memory преди 10 месеца
  Daniel Hiltgen 3518aaef33 Merge pull request #4218 from dhiltgen/auto_parallel преди 10 месеца
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) преди 10 месеца
  Daniel Hiltgen 17b7186cd7 Enable concurrency by default преди 1 година
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental преди 10 месеца
  Daniel Hiltgen 6f351bf586 review comments and coverage преди 11 месеца
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility преди 11 месеца
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit преди 11 месеца
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) преди 10 месеца
  Michael Yang e40145a39d lint преди 11 месеца