Commit History

Author SHA1 Message Date
  Roy Han eb7cc2d1ce image embeddings 9 months ago
  royjhan b7c622dd32 Merge branch 'main' into royh-batchembed 9 months ago
  Daniel Hiltgen af28b94533 Merge pull request #5469 from dhiltgen/prevent_system_oom 10 months ago
  Daniel Hiltgen 955f2a4e03 Only set default keep_alive on initial model load 10 months ago
  Daniel Hiltgen 3c75113e37 Prevent loading models larger than total memory 10 months ago
  Roy Han 6caac01494 clear comments 10 months ago
  Roy Han 17de2b4405 Refactoring of legacy and new 10 months ago
  royjhan a5f23d766e Merge branch 'main' into royh-batchembed 10 months ago
  Roy Han 00a4cb26ca use float32 10 months ago
  Daniel Hiltgen 3518aaef33 Merge pull request #4218 from dhiltgen/auto_parallel 10 months ago
  Roy Han 49e341147d add server function 10 months ago
  Roy Han c406fa7a4c api/embed draft 10 months ago
  Roy Han ff191d7cba Initial Draft 10 months ago
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 months ago
  Roy Han 0f87628b6d Revert "Initial Batch Embedding" 10 months ago
  Daniel Hiltgen 17b7186cd7 Enable concurrency by default 1 year ago
  Roy Han c22d54895a Initial Batch Embedding 10 months ago
  Daniel Hiltgen 45cacbaf05 Merge pull request #4517 from dhiltgen/gpu_incremental 10 months ago
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 months ago
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 months ago
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 months ago
  Jeffrey Morgan dd7c9ebeaf server: longer timeout in `TestRequests` (#5046) 10 months ago
  Michael Yang e40145a39d lint 11 months ago
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 months ago
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 months ago
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 11 months ago
  Daniel Hiltgen 0a954e5066 Fix stale test logic 1 year ago
  Jeffrey Morgan dfa2f32ca0 unload in critical section (#4187) 1 year ago
  Daniel Hiltgen f56aa20014 Centralize server config handling 1 year ago
  Daniel Hiltgen 9a32c514cb Soften timeouts on sched unit tests 1 year ago