Commit graph

Select branches

Hide pull requests

master

Mono Color

• 67472e0e89
  Also flag *.icns as binary Nicholas42 2024-08-09 13:41:20 +0200
• e9aa5117c4
  Merge pull request #6133 from dhiltgen/cuda_repo Daniel Hiltgen 2024-08-08 12:33:35 -0700
• 2473bdba5e
  Merge pull request #6182 from dhiltgen/more_patterns Daniel Hiltgen 2024-08-08 12:33:17 -0700
• 2003d60159 llama3.1 memory Michael Yang 2024-08-08 11:18:13 -0700
• 7d1c0047fa
  Merge pull request #6247 from ollama/jessegross/layers Jesse Gross 2024-08-08 10:46:43 -0700
• 7b61eba471 server/download.go: Fix a typo in log Jitang Lei 2024-08-08 20:28:01 +0800
• 7edaf6e7e8 manifest: Store layers inside manifests consistently as values. Jesse Gross 2024-08-07 14:22:17 -0700
• 97ec8cfd4e image: Clarify argument to WriteManifest is config Jesse Gross 2024-08-07 11:44:25 -0700
• 5b3a21b578
  add metrics to docs (#6079) royjhan 2024-08-07 17:43:44 -0400
• ad0c19dde4
  Use llama3.1 in tools example (#5985) Kyle Kelley 2024-08-07 14:20:50 -0700
• 69eb06c40e
  Merge pull request #6145 from ollama/jessegross/bug5840 Jesse Gross 2024-08-07 11:24:15 -0700
• 1829fb61bd manifest: Fix crash on startup when trying to clean up unused files (#5840) Jesse Gross 2024-08-05 17:13:52 -0700
• ce67706037 Set *.png and *.ico to be treated as binary files. Nicholas Schwab 2024-08-07 18:15:17 +0200
• 685a53534b manifest: Don't prune layers if we can't open a manifest file Jesse Gross 2024-08-01 15:05:16 -0700
• de4fc29773
  llm: reserve required number of slots for embeddings (#6219) Jeffrey Morgan 2024-08-06 23:20:49 -0400
• e04c7012c2
  update llama.cpp submodule to 1e6f6554 (#6208) Jeffrey Morgan 2024-08-06 15:11:45 -0400
• d4a7216c82
  Fixed invalid option provided not displaying the invalid option name problem. (#6202) Chua Chee Seng 2024-08-07 02:37:16 +0800
• a4fdd03c3b
  Merge pull request #6207 from dhiltgen/sparse_win Daniel Hiltgen 2024-08-06 11:06:06 -0700
• fc85f50a2b Ensure sparse files on windows during download Daniel Hiltgen 2024-08-06 10:46:31 -0700
• f2d1c842ad
  
  Merge https://github.com/ollama/ollama baalajimaestro 2024-08-06 08:21:56 +0530
• 86b907f82a
  sort batch results (#6189) royjhan 2024-08-05 19:55:34 -0400
• 10d49bce70
  Merge pull request #6190 from ollama/mxyng/fix-integration Michael Yang 2024-08-05 16:45:49 -0700
• 7ed367419e fix concurrency test Michael Yang 2024-08-05 16:34:54 -0700
• 50ee8b5f56
  Merge pull request #6186 from dhiltgen/numa Daniel Hiltgen 2024-08-05 15:20:06 -0700
• 03bdac0595
  Merge pull request #6146 from ollama/mxyng/testing Michael Yang 2024-08-05 13:00:05 -0700
• f457d63400 Implement linux NUMA detection Daniel Hiltgen 2024-08-05 12:56:20 -0700
• 04210aa6dd Catch one more error log Daniel Hiltgen 2024-08-05 09:28:07 -0700
• 43f9d92008 close pid file Michael Yang 2024-08-05 00:34:09 -0700
• ed6c8bfe57 removeall to remove non-empty temp dirs Michael Yang 2024-08-05 00:02:47 -0700
• 39f2bc6bfc
  Merge pull request #6167 from ollama/mxyng/line-feed Michael Yang 2024-08-05 00:06:28 -0700
• b73b0940ef
  Disable paging for journalctl (#6154) frob 2024-08-05 06:10:53 +0200
• 6a07344786 line feed Michael Yang 2024-08-04 17:25:33 -0700
• 8b920f35a4
  Add Gemma 2 2b (#6151) sryu1 2024-08-05 00:58:39 +1000
• 4221e39867
  Reference ollama integration with Harbor (#6147) Ivan Charapanau 2024-08-03 02:03:46 +0200
• a091fadfda use testing tempdirs Michael Yang 2024-08-02 15:55:34 -0700
• 77ccbf04dc
  Merge pull request #6128 from ollama/mxyng/lint Michael Yang 2024-08-02 14:58:40 -0700
• 4addf6b587
  Update OpenAI Compatibility Docs with /v1/completions (#5311) royjhan 2024-08-02 16:16:23 -0400
• 85c7f11170
  Update docs (#5310) royjhan 2024-08-02 16:05:57 -0400
• a89cde8ab6
  
  Merge https://github.com/ollama/ollama baalajimaestro 2024-08-02 17:38:58 +0530
• df3802a65f Adjust arm cuda repo paths Daniel Hiltgen 2024-08-01 17:22:25 -0700
• b732beba6a lint Michael Yang 2024-08-01 14:52:15 -0700
• ce1fb4447e
  Fix models/{model} URL (#6132) Kim Hallberg 2024-08-02 01:31:47 +0200
• 558a54b098
  Update OpenAI Compatibility Docs with /v1/embeddings (#5470) royjhan 2024-08-01 19:00:29 -0400
• ed52833bb1
  Add to docs (#5309) royjhan 2024-08-01 18:58:13 -0400
• 6f133a0bdd
  OpenAI: Add Usage to v1/embeddings (#5886) royjhan 2024-08-01 18:49:37 -0400
• f561eecfb8
  Update OpenAI Compatibility Docs with /v1/models (#5151) royjhan 2024-08-01 18:48:44 -0400
• ff7c9060ec
  Merge pull request #6115 from slouffka/fix-context Michael Yang 2024-08-01 15:13:59 -0700
• 0ff42e84b0
  Merge pull request #4756 from ollama/mxyng/convert2 Michael Yang 2024-08-01 14:16:30 -0700
• 8a9f946ca7 Refactor and format code. Vyacheslav Moskalev 2024-08-02 03:50:05 +0700
• 3b5210548e Refactor code. Remove extra variable. Vyacheslav Moskalev 2024-08-01 19:56:15 +0700
• b0c216584c Better types and naming closer to style. Vyacheslav Moskalev 2024-08-01 19:43:44 +0700
• 49a5483139 Change the order of context and prompt. Vyacheslav Moskalev 2024-08-01 19:25:56 +0700
• 6bc5c13758 Fix extra context concatenation in generate handler (#5980). Vyacheslav Moskalev 2024-08-01 15:45:41 +0700
• 3e614260af
  Merge pull request #6109 from ollama/mxyng/fix-modelfile Michael Yang 2024-07-31 17:05:43 -0700
• d87b4a488e fix modelfile message quotes Michael Yang 2024-07-31 16:52:09 -0700
• 4c14855ad7
  Merge pull request #6106 from ollama/mxyng/default-sliding-window-attention Michael Yang 2024-07-31 16:12:06 -0700
• dc77bbcfa4
  server: fix json marshalling of downloadBlobPart (#6108) Blake Mizerany 2024-07-31 16:01:24 -0700
• d8e2664c33 convert: fix parse functions Michael Yang 2024-07-31 15:39:11 -0700
• eafc607abb convert: only extract large files Michael Yang 2024-06-29 16:53:59 -0700
• 781fc2d576 Update convert/reader_safetensors.go Michael Yang 2024-07-31 10:58:22 -0700
• df993fa37b comments Michael Yang 2024-07-08 16:59:48 -0700
• 5e9db9fb0b refactor convert Michael Yang 2024-05-31 20:00:49 -0700
• 0f3271db88 patches: phi3 default sliding window attention Michael Yang 2024-07-31 14:48:06 -0700
• 6b252918fb update convert test to check result data Michael Yang 2024-06-03 09:49:13 -0700
• c4c84b7a0d
  Merge pull request #5196 from ollama/mxyng/messages-2 Michael Yang 2024-07-31 10:18:17 -0700
• 5c1912769e
  Merge pull request #5473 from ollama/mxyng/environ Michael Yang 2024-07-31 10:18:05 -0700
• 71399aa682
  Added BoltAI as a desktop UI for Ollama (#6096) Daniel Nguyen 2024-07-31 22:44:58 +0700
• f564d9cbc1
  
  Merge https://github.com/ollama/ollama baalajimaestro 2024-07-31 18:09:46 +0530
• 463a8aa273
  Create SECURITY.md Jeffrey Morgan 2024-07-30 21:01:12 -0700
• 3579b4966a
  Update README to include Firebase Genkit (#6083) Michael 2024-07-30 18:40:09 -0700
• 5d66578356
  Update README.md Jeffrey Morgan 2024-07-30 18:08:34 -0700
• afa8d6e9d5 patch gemma support jmorganca 2024-07-30 18:06:26 -0700
• 1b44d873e7
  Add Metrics to api\embed response (#5709) royjhan 2024-07-30 13:12:21 -0700
• cef2c6054d
  Merge pull request #5859 from dhiltgen/homogeneous_gpus Daniel Hiltgen 2024-07-30 11:06:42 -0700
• 345420998e Prevent partial loading on mixed GPU brands Daniel Hiltgen 2024-07-22 11:57:26 -0700
• 0be8baad2b
  Update and Fix example models (#6065) Kim Hallberg 2024-07-30 08:56:37 +0200
• 1a83581a8e
  Merge pull request #5895 from dhiltgen/sched_faq Daniel Hiltgen 2024-07-29 14:25:41 -0700
• 37926eb991
  Merge pull request #5927 from dhiltgen/high_cpu_count Daniel Hiltgen 2024-07-29 14:24:57 -0700
• 3d4634fdff
  Merge pull request #5934 from dhiltgen/missing_cuda_repo Daniel Hiltgen 2024-07-29 14:24:20 -0700
• 365431d406
  return tool calls finish reason for openai (#5995) royjhan 2024-07-29 13:56:57 -0700
• 161e12cecf
  Merge pull request #5932 from dhiltgen/win_font Daniel Hiltgen 2024-07-29 13:40:24 -0700
• 46e6327e0f
  api: add stringifier for Tool (#5891) Jeffrey Morgan 2024-07-29 13:35:16 -0700
• 68ee42f995
  update llama.cpp submodule to 6eeaeba1 (#6039) Jeffrey Morgan 2024-07-29 13:20:26 -0700
• f26aef9a8b
  docs: update README.md (#6059) Ikko Eltociear Ashimine 2024-07-30 02:53:30 +0900
• 38d9036b59
  Merge pull request #5992 from ollama/mxyng/save Michael Yang 2024-07-29 09:53:19 -0700
• 6f26e9322f
  Fix typo in image docs (#6041) Veit Heller 2024-07-29 17:50:53 +0200
• 0e4d653687
  upate to llama3.1 elsewhere in repo (#6032) Jeffrey Morgan 2024-07-28 19:56:02 -0700
• 2c01610616
  update readme to llama3.1 (#5933) Michael 2024-07-28 17:21:38 -0400
• f3d7a481b7
  feat: add support for min_p (resolve #1142) (#1825) Tibor Schmidt 2024-07-27 23:37:40 +0200
• f2a96c7d77
  llm: keep patch for llama 3 rope factors (#5987) Jeffrey Morgan 2024-07-26 18:20:52 -0400
• e8a66680d1
  Merge pull request #5705 from dhiltgen/win_errormode Daniel Hiltgen 2024-07-26 14:49:34 -0700
• 079b2c3b03
  Merge pull request #5999 from ollama/mxyng/fix-push Michael Yang 2024-07-26 14:28:34 -0700
• 750c1c55f7
  server: fix race conditions during download (#5994) Blake Mizerany 2024-07-26 14:24:24 -0700
• a622c47bd3 fix nil deref in auth.go Michael Yang 2024-07-26 14:10:18 -0700
• ec4c35fe99
  Merge pull request #5512 from ollama/mxyng/detect-stop Michael Yang 2024-07-26 13:48:23 -0700
• a250c2cb13 display messages Michael Yang 2024-07-26 13:39:38 -0700
• 3d9de805b7 fix: model save Michael Yang 2024-07-26 13:19:01 -0700
• 15af558423 include modelfile messages Michael Yang 2024-06-19 14:14:28 -0700
• f5e3939220
  Update api.md (#5968) Jeffrey Morgan 2024-07-25 23:10:18 -0400
• ae27d9dcfd
  Update openai.md Jeffrey Morgan 2024-07-25 20:27:33 -0400