Komit Sejarah

Pembuat SHA1 Pesan Tanggal
  royjhan b7c622dd32 Merge branch 'main' into royh-batchembed 10 bulan lalu
  Daniel Hiltgen af28b94533 Merge pull request #5469 from dhiltgen/prevent_system_oom 10 bulan lalu
  Daniel Hiltgen 955f2a4e03 Only set default keep_alive on initial model load 10 bulan lalu
  Daniel Hiltgen 3c75113e37 Prevent loading models larger than total memory 10 bulan lalu
  Roy Han 6caac01494 clear comments 10 bulan lalu
  Roy Han 17de2b4405 Refactoring of legacy and new 10 bulan lalu
  royjhan a5f23d766e Merge branch 'main' into royh-batchembed 10 bulan lalu
  Roy Han 00a4cb26ca use float32 10 bulan lalu
  Daniel Hiltgen 3518aaef33 Merge pull request #4218 from dhiltgen/auto_parallel 10 bulan lalu
  Roy Han 49e341147d add server function 10 bulan lalu
  Roy Han c406fa7a4c api/embed draft 10 bulan lalu
  Roy Han ff191d7cba Initial Draft 10 bulan lalu
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 bulan lalu
  Roy Han 0f87628b6d Revert "Initial Batch Embedding" 10 bulan lalu
  Daniel Hiltgen 17b7186cd7 Enable concurrency by default 1 tahun lalu
  Roy Han c22d54895a Initial Batch Embedding 10 bulan lalu
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental 10 bulan lalu
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 bulan lalu
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 bulan lalu
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 bulan lalu
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) 10 bulan lalu
  Michael Yang e40145a39d lint 11 bulan lalu
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 bulan lalu
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 bulan lalu
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 1 tahun lalu
  Daniel Hiltgen 0a954e5066 Fix stale test logic 1 tahun lalu
  Jeffrey Morgan dfa2f32ca0 unload in critical section (#4187) 1 tahun lalu
  Daniel Hiltgen f56aa20014 Centralize server config handling 1 tahun lalu
  Daniel Hiltgen 9a32c514cb Soften timeouts on sched unit tests 1 tahun lalu
  Daniel Hiltgen d6e3b64582 Fix concurrency for CPU mode 1 tahun lalu