Commit Graph

  • e9d15eb277 remove build scripts jmorganca 2024-06-10 02:56:37 -04:00
  • 4051a26f6f remove need for perl jmorganca 2024-06-10 00:04:21 -04:00
  • a687913a97 fix output jmorganca 2024-06-09 23:53:40 -04:00
  • 6110d25dce arch build jmorganca 2024-06-09 20:19:11 -07:00
  • 2081ec9ba1 add temporary makefile jmorganca 2024-06-09 22:33:31 -04:00
  • 4b13e564eb fix cuda and rocm builds jmorganca 2024-06-09 19:49:22 -04:00
  • 34015ca10d fix cgo flags for darwin amd64 jmorganca 2024-06-09 14:30:41 -07:00
  • 11508826b2 remove -fPIC from build_hipblas.sh jmorganca 2024-06-07 12:52:49 -04:00
  • ac090b6b71 fix issues with runner jmorganca 2024-06-07 09:32:52 -07:00
  • 6dab2a9d3a move sync script back in for now jmorganca 2024-06-07 09:26:44 -07:00
  • 834aac8450 llama: sync jmorganca 2024-06-07 00:27:24 -07:00
  • ac6b154cc4 update to d5c938cd jmorganca 2024-06-07 00:15:58 -07:00
  • 0574fe199a add patches jmorganca 2024-06-06 23:55:47 -07:00
  • 028fda3582 cleanup stop code jmorganca 2024-06-04 00:58:58 -07:00
  • 8ef58a6695 fix example jmorganca 2024-06-04 00:43:03 -07:00
  • b9db5ab5d0 revert llm changes jmorganca 2024-06-04 00:40:19 -07:00
  • a796b7aeaf num predict jmorganca 2024-05-28 23:38:44 -07:00
  • 89cb4b8d6b basic progress jmorganca 2024-05-28 23:11:48 -07:00
  • 0d365e8d34 add more runner params jmorganca 2024-05-28 00:02:01 -07:00
  • 72ff94efe0 truncate stop properly jmorganca 2024-05-27 23:09:56 -07:00
  • 240d4cf0aa wip stop tokens jmorganca 2024-05-27 14:38:44 -07:00
  • 424627c347 embeddings jmorganca 2024-05-27 11:33:47 -07:00
  • 1a801fba2a remove dependency on llm jmorganca 2024-05-26 23:23:09 -07:00
  • 727494ea54 grammar jmorganca 2024-05-26 23:14:44 -07:00
  • b39fca7088 sampling jmorganca 2024-05-26 23:01:05 -07:00
  • db55b1b89d better example module, add port jmorganca 2024-05-25 20:11:57 -07:00
  • 1124e24aff wip jmorganca 2024-05-24 10:09:35 -07:00
  • df44d119a3 add llava to runner jmorganca 2024-05-23 18:22:15 -07:00
  • 86955c3014 fix output in build_hipblas.sh jmorganca 2024-05-20 16:43:53 -07:00
  • c05ba504ef mods to build_hipblas.sh for linux jmorganca 2024-05-20 16:15:16 -07:00
  • aaca2ce093 wip jmorganca 2024-05-20 15:27:10 -07:00
  • 921708003e improve cuda and hipblas build scripts jmorganca 2024-05-20 16:17:13 -04:00
  • 323a3f1f3a cuda linux jmorganca 2024-05-19 23:11:30 -07:00
  • 07d6e589ca Update README.md Jeffrey Morgan 2024-05-19 16:47:50 -07:00
  • aa52dfcaaf Update README.md Jeffrey Morgan 2024-05-19 16:47:19 -07:00
  • 31e0de825e disable log file jmorganca 2024-05-19 16:36:32 -07:00
  • d65b4ea480 fix readme for llava jmorganca 2024-05-19 16:33:37 -07:00
  • 878eb9a19f add llava jmorganca 2024-05-19 16:30:11 -07:00
  • 5818e3b210 llama: add clip dependencies jmorganca 2024-05-19 14:06:46 -07:00
  • 2a41ad5b1f add clip and parallel requests to the todo list jmorganca 2024-05-19 14:01:52 -07:00
  • cf1ec78071 fix cuda build jmorganca 2024-05-19 03:34:24 -04:00
  • 57d03929cd fix build on windows jmorganca 2024-05-19 03:19:41 -04:00
  • 0a6b1adbd7 fix ggml-metal.m build constraints jmorganca 2024-05-19 00:10:15 -07:00
  • ec60d79a67 fix ggml-metal.m jmorganca 2024-05-19 00:06:26 -07:00
  • 3d656588a7 avx2 should only add avx2 jmorganca 2024-05-18 23:53:29 -07:00
  • 460d9857e2 fix sync script jmorganca 2024-05-18 23:50:50 -07:00
  • a5548a81fc fix ggml-metal.m jmorganca 2024-05-18 23:34:58 -07:00
  • 634f6a75d0 fix ggml-metal.m jmorganca 2024-05-18 23:31:41 -07:00
  • 3b5e5a6280 add license headers jmorganca 2024-05-18 23:30:28 -07:00
  • 853d96b1b1 pre-patch jmorganca 2024-05-18 23:27:01 -07:00
  • 4dd63c1fef move runner package down jmorganca 2024-05-18 23:15:51 -07:00
  • 82214396b5 replace static build in llm jmorganca 2024-05-18 22:22:46 -07:00
  • 8ca4a9a70a fix build jmorganca 2024-05-18 21:23:53 -07:00
  • 25fd8fd045 wip... jmorganca 2024-05-16 13:52:38 -07:00
  • be2f37b5d4 rename server to runner jmorganca 2024-05-19 00:13:30 -04:00
  • 9e28405c54 Update README.md Jeffrey Morgan 2024-05-18 19:50:23 -07:00
  • 9f3e950120 Update README.md Jeffrey Morgan 2024-05-18 19:49:43 -07:00
  • 951104045f Update README.md Jeffrey Morgan 2024-05-18 19:47:19 -07:00
  • 597712006c Update README.md Jeffrey Morgan 2024-05-18 19:46:44 -07:00
  • 64e712b12b Add missing hipcc flags jmorganca 2024-05-18 23:07:19 -04:00
  • 85aea62997 fix .gitattributes jmorganca 2024-05-18 22:39:41 -04:00
  • 491ff41675 Initial llama Go module jmorganca 2024-04-20 20:44:01 -04:00
  • 075f2e88d9 add sync of llama.cpp jmorganca 2024-04-20 18:08:09 -04:00
  • cf7344b221 close files Josh Yan 2024-07-29 15:05:40 -07:00
  • 3cd1c9baa9 refactor test Josh Yan 2024-07-29 14:57:37 -07:00
  • e5f03af4d3 refactor test Josh Yan 2024-07-29 14:57:23 -07:00
  • 372e4e9ea4
    Merge 92c0cc4fb4b0bc9f4a70a2aeeab450f2bfb52b49 into 1a83581a8e1063418f5f1fec14638409d0681b68 Daniel Hiltgen 2024-07-29 14:55:32 -07:00
  • b669677be9 refactor test Josh Yan 2024-07-29 14:54:18 -07:00
  • 86a874fceb fmt Josh Yan 2024-07-29 14:37:21 -07:00
  • 18203bf8d8 reword err Josh Yan 2024-07-29 14:35:55 -07:00
  • aaa1c08a5d testing and FROM local version copy Josh Yan 2024-07-29 14:30:03 -07:00
  • 1a83581a8e
    Merge pull request #5895 from dhiltgen/sched_faq Daniel Hiltgen 2024-07-29 14:25:41 -07:00
  • 37926eb991
    Merge pull request #5927 from dhiltgen/high_cpu_count Daniel Hiltgen 2024-07-29 14:24:57 -07:00
  • 3d4634fdff
    Merge pull request #5934 from dhiltgen/missing_cuda_repo Daniel Hiltgen 2024-07-29 14:24:20 -07:00
  • 1862a82141 list metrics Roy Han 2024-07-29 14:14:53 -07:00
  • 365431d406
    return tool calls finish reason for openai (#5995) royjhan 2024-07-29 13:56:57 -07:00
  • 18e92c5209 move to openai Roy Han 2024-07-29 13:46:06 -07:00
  • 5ae3dda1b6 finish reason Roy Han 2024-07-29 13:44:51 -07:00
  • 161e12cecf
    Merge pull request #5932 from dhiltgen/win_font Daniel Hiltgen 2024-07-29 13:40:24 -07:00
  • 46e6327e0f
    api: add stringifier for Tool (#5891) Jeffrey Morgan 2024-07-29 13:35:16 -07:00
  • ab9dfbddea OLLAMA version Josh Yan 2024-07-29 13:24:50 -07:00
  • 68ee42f995
    update llama.cpp submodule to 6eeaeba1 (#6039) Jeffrey Morgan 2024-07-29 13:20:26 -07:00
  • e1ac4d32c3 clean up Roy Han 2024-07-29 11:20:21 -07:00
  • 9c2449122e backend stream support Roy Han 2024-07-29 11:16:06 -07:00
  • 8e74ef738a
    Merge 4b4e97ed103f07002503076ebc250cd08f88a367 into f26aef9a8bfdd3e0f0d13cafe8bd371f29d9d877 Michael Yang 2024-07-29 10:57:35 -07:00
  • f26aef9a8b
    docs: update README.md (#6059) Ikko Eltociear Ashimine 2024-07-30 02:53:30 +09:00
  • 43fc936405
    docs: update README.md Ikko Eltociear Ashimine 2024-07-30 02:36:38 +09:00
  • 38d9036b59
    Merge pull request #5992 from ollama/mxyng/save Michael Yang 2024-07-29 09:53:19 -07:00
  • 6f26e9322f
    Fix typo in image docs (#6041) Veit Heller 2024-07-29 17:50:53 +02:00
  • ef826e5790 Added reference to Llama.cpp docs for passed through API options Lennart J. Kurzweg (Nx2) 2024-07-29 16:53:19 +02:00
  • b6470dc67a
    docs: Add ingest to list of cli tools Sam 2024-07-30 00:33:23 +10:00
  • 4e932fe908
    Fix typo in image docs Veit Heller 2024-07-29 11:37:55 +02:00
  • f38700ecf7 update llama.cpp submodule to 6eeaeba1 jmorganca 2024-07-28 19:15:17 -07:00
  • 0e4d653687
    upate to llama3.1 elsewhere in repo (#6032) Jeffrey Morgan 2024-07-28 19:56:02 -07:00
  • 529627e358
    Update install.sh:Replace "command -v" with encapsulated functionality 王卿 2024-07-29 10:12:15 +08:00
  • afe0d199c9 Enhance windows ROCm compatibility Daniel Hiltgen 2024-07-28 13:15:05 -07:00
  • 8e3d9d0b05 upate to llama3.1 elsewhere in repo jmorganca 2024-07-28 14:22:25 -07:00
  • 2c01610616
    update readme to llama3.1 (#5933) Michael 2024-07-28 17:21:38 -04:00
  • f3d7a481b7
    feat: add support for min_p (resolve #1142) (#1825) Tibor Schmidt 2024-07-27 23:37:40 +02:00
  • da6c33d9ea
    Merge e5b1b110ba186d9cdcdd80d28143eb9595145f13 into f2a96c7d778249a7f911471b6a1532339e42fcf5 Thomas Lavoie 2024-07-27 20:38:39 +00:00