Commit Graph

  • f852cf1be1 revert llm changes jmorganca 2024-06-04 00:40:19 -07:00
  • 3ac16286fc num predict jmorganca 2024-05-28 23:38:44 -07:00
  • 1bc7b8fa4c basic progress jmorganca 2024-05-28 23:11:48 -07:00
  • 6d3e75f5b0 add more runner params jmorganca 2024-05-28 00:02:01 -07:00
  • 4848826f55 truncate stop properly jmorganca 2024-05-27 23:09:56 -07:00
  • 9c511dc453 wip stop tokens jmorganca 2024-05-27 14:38:44 -07:00
  • 9c65dff00d embeddings jmorganca 2024-05-27 11:33:47 -07:00
  • cfb080cb6f remove dependency on llm jmorganca 2024-05-26 23:23:09 -07:00
  • 5b86e29804 grammar jmorganca 2024-05-26 23:14:44 -07:00
  • 271c0f5722 sampling jmorganca 2024-05-26 23:01:05 -07:00
  • d6a8828d6b better example module, add port jmorganca 2024-05-25 20:11:57 -07:00
  • b7f405217b wip jmorganca 2024-05-24 10:09:35 -07:00
  • 457ee74c3c add llava to runner jmorganca 2024-05-23 18:22:15 -07:00
  • f03299e8bc fix output in build_hipblas.sh jmorganca 2024-05-20 16:43:53 -07:00
  • 22d45b1661 mods to build_hipblas.sh for linux jmorganca 2024-05-20 16:15:16 -07:00
  • 638a3642f0 wip jmorganca 2024-05-20 15:27:10 -07:00
  • 6463cb0683 improve cuda and hipblas build scripts jmorganca 2024-05-20 16:17:13 -04:00
  • 63d730eef3 cuda linux jmorganca 2024-05-19 23:11:30 -07:00
  • 256e00c5f2 Update README.md Jeffrey Morgan 2024-05-19 16:47:50 -07:00
  • 72bfdbbd7c Update README.md Jeffrey Morgan 2024-05-19 16:47:19 -07:00
  • 1ad1e7d543 disable log file jmorganca 2024-05-19 16:36:32 -07:00
  • 979255f84a fix readme for llava jmorganca 2024-05-19 16:33:37 -07:00
  • a56c8a128c add llava jmorganca 2024-05-19 16:30:11 -07:00
  • 42dfb8d66c llama: add clip dependencies jmorganca 2024-05-19 14:06:46 -07:00
  • b8b643ad54 add clip and parallel requests to the todo list jmorganca 2024-05-19 14:01:52 -07:00
  • 0653c9e8bf fix cuda build jmorganca 2024-05-19 03:34:24 -04:00
  • 94ffc581f0 fix build on windows jmorganca 2024-05-19 03:19:41 -04:00
  • a90e3c31cf fix ggml-metal.m build constraints jmorganca 2024-05-19 00:10:15 -07:00
  • 05c896db87 fix ggml-metal.m jmorganca 2024-05-19 00:06:26 -07:00
  • 1a22dbb4fd avx2 should only add avx2 jmorganca 2024-05-18 23:53:29 -07:00
  • 0bf12dae37 fix sync script jmorganca 2024-05-18 23:50:50 -07:00
  • c8299bdb5b fix ggml-metal.m jmorganca 2024-05-18 23:34:58 -07:00
  • f825b31266 fix ggml-metal.m jmorganca 2024-05-18 23:31:41 -07:00
  • ae8b834c39 add license headers jmorganca 2024-05-18 23:30:28 -07:00
  • 7ba84b145f pre-patch jmorganca 2024-05-18 23:27:01 -07:00
  • 3a1d5febaf move runner package down jmorganca 2024-05-18 23:15:51 -07:00
  • cdc493ed4e replace static build in llm jmorganca 2024-05-18 22:22:46 -07:00
  • 7749986151 fix build jmorganca 2024-05-18 21:23:53 -07:00
  • ad64db1a63 wip... jmorganca 2024-05-16 13:52:38 -07:00
  • c08bb0b107 rename server to runner jmorganca 2024-05-19 00:13:30 -04:00
  • 6b3e946f69 Update README.md Jeffrey Morgan 2024-05-18 19:50:23 -07:00
  • 87868a9418 Update README.md Jeffrey Morgan 2024-05-18 19:49:43 -07:00
  • 9b11f272de Update README.md Jeffrey Morgan 2024-05-18 19:47:19 -07:00
  • 00a8a37bda Update README.md Jeffrey Morgan 2024-05-18 19:46:44 -07:00
  • 211a8b0290 Add missing hipcc flags jmorganca 2024-05-18 23:07:19 -04:00
  • 8523233d55 fix .gitattributes jmorganca 2024-05-18 22:39:41 -04:00
  • c815358a81 Initial llama Go module jmorganca 2024-04-20 20:44:01 -04:00
  • adafbf9081 add sync of llama.cpp jmorganca 2024-04-20 18:08:09 -04:00
  • 25367d034f adding Archyve to community integrations list nickthecook 2024-08-31 18:26:20 -04:00
  • 56318fb365
    Improve logging on GPU too small (#6666) Daniel Hiltgen 2024-09-06 08:29:36 -07:00
  • 79dd7b7cce
    Merge branch 'ollama:main' into presence_penalty frob 2024-09-06 16:08:15 +02:00
  • c9f26c4a5c
    Merge 3c37700c6e5db5d3e509049da0805ee8d853ed1b into fe91d7fff13cc48879b320911a9662f08a686264 Iván García 2024-09-06 23:02:28 +12:00
  • 4b3d241372 update windows build ZheWang 2024-09-06 12:44:14 +08:00
  • f4a5b36c32
    fixed return URL when status is ok Tobias Heinze 2024-09-06 11:43:44 +02:00
  • fe91d7fff1
    openai: fix "presence_penalty" typo and add test (#6665) frob 2024-09-06 10:16:28 +02:00
  • 116992a4c2
    Merge 5a67f93eae5a3f6d08af4f2d9015ace86d4cb550 into 608e87bf8707e377f1c195ae22330e26f67de91e Jeffrey Morgan 2024-09-06 10:43:49 +08:00
  • 6e86ed412e
    Update README.md wallacelance 2024-09-06 07:57:19 +05:30
  • dc58f80afd lint Wang,Zhe 2024-09-06 09:57:07 +08:00
  • 534cacb76e update Wang,Zhe 2024-08-09 12:49:10 +08:00
  • 828ca42c65 fix old lze driver crash ZheWang 2024-07-22 09:56:24 +08:00
  • 1449e4e066 add force enable inteligpu env var Wang,Zhe 2024-07-22 08:53:41 +08:00
  • c9283ca9ae lint Wang,Zhe 2024-07-19 17:24:39 +08:00
  • 62ab5633a6 new igpu used system-ram command Wang,Zhe 2024-07-18 11:45:16 +08:00
  • 58e4bdf8d2 Update gpu/gpu.go Wang, Zhe 2024-07-18 09:09:38 +08:00
  • a6cb1593d2 remove reg match Wang,Zhe 2024-07-17 13:14:09 +08:00
  • 2472e7e4ce igpu discovery refactor on windows platform Wang,Zhe 2024-07-17 12:35:05 +08:00
  • 902e27f1b9 igpu discovery refactor on linux platform Wang,Zhe 2024-07-17 11:54:41 +08:00
  • 467a5558fc fix typo Wang,Zhe 2024-07-11 09:55:58 +08:00
  • 4a23ed2d97 fix windows ZheWang 2024-07-11 09:19:15 +08:00
  • c484e2820e support windows Wang,Zhe 2024-07-10 17:39:45 +08:00
  • bfc32f94fc support intel igpus Wang,Zhe 2024-07-10 17:22:10 +08:00
  • b0f386d9c9 Improve logging on GPU too small Daniel Hiltgen 2024-09-05 17:21:56 -07:00
  • c26a5b9165
    Merge branch 'ollama:main' into presence_penalty frob 2024-09-06 02:19:48 +02:00
  • ed7673b39a gofumpt-ify changes. Richard Lyons 2024-09-06 02:17:50 +02:00
  • 608e87bf87
    Fix gemma2 2b conversion (#6645) v0.3.10-rc1 Patrick Devine 2024-09-05 17:02:28 -07:00
  • b7bafd4d09 Fix "presence_penalty_penalty" typo, add test. Richard Lyons 2024-09-06 01:55:27 +02:00
  • ceca79174c comments Patrick Devine 2024-09-05 16:45:57 -07:00
  • 48685c6ed0
    Document uninstall on windows (#6663) Daniel Hiltgen 2024-09-05 15:57:38 -07:00
  • 383c84ec87 Document uninstall on windows Daniel Hiltgen 2024-09-05 15:21:40 -07:00
  • e326093618 feed the linter Patrick Devine 2024-09-05 15:16:36 -07:00
  • bd7e451f3e catch duplicate tensor names Patrick Devine 2024-09-05 15:12:34 -07:00
  • 9565fa64a8
    Revert "Detect running in a container (#6495)" (#6662) Daniel Hiltgen 2024-09-05 14:26:00 -07:00
  • a677087272
    Revert "Detect running in a container (#6495)" Daniel Hiltgen 2024-09-05 14:19:56 -07:00
  • 6719097649
    llm: make load time stall duration configurable via OLLAMA_LOAD_TIMEOUT Daniel Hiltgen 2024-09-05 14:00:08 -07:00
  • 031b6c96bb Make stall duration timeout configurable Daniel Hiltgen 2024-09-03 10:40:11 -07:00
  • b05c9e83d9
    Introduce GPU Overhead env var (#5922) Daniel Hiltgen 2024-09-05 13:46:35 -07:00
  • f3bd31f4e8 Detect running in a container follow up Daniel Hiltgen 2024-09-05 13:41:17 -07:00
  • a60d9b89ce
    Detect running in a container (#6495) Daniel Hiltgen 2024-09-05 13:24:51 -07:00
  • bf612cd608
    Merge pull request #6260 from ollama/mxyng/mem Michael Yang 2024-09-05 13:22:08 -07:00
  • ef98e56122
    readme: add AiLama to the list of community integrations (#4957) Zeyo 2024-09-06 01:40:44 +05:30
  • 38acaf550e
    Update README.md Jeffrey Morgan 2024-09-05 13:09:57 -07:00
  • 4432069bd7
    Merge branch 'main' into main Zeyo 2024-09-06 00:04:01 +05:30
  • 5f944baac7
    Update gpu.md: Add RTX 3050 Ti and RTX 3050 Ti (#5888) Michael 2024-09-05 12:24:26 -06:00
  • bc8ae8503b
    Update gpu.md Michael 2024-09-05 12:19:50 -06:00
  • 6fc9d22707
    server: fix blob download when receiving a 200 response (#6656) Tobias Heinze 2024-09-05 19:48:26 +02:00
  • f27c00d8c5
    readme: add Gentoo package manager entry to community integrations (#5714) Vitaly Zdanevich 2024-09-05 20:58:14 +04:00
  • c7c845ec52
    Update install.sh:Replace "command -v" with encapsulated functionality (#6035) 王卿 2024-09-06 00:49:48 +08:00
  • a72b666076
    Fixed if direct url is already present Tobias Heinze 2024-09-05 14:32:00 +02:00
  • ec486370fa
    Merge branch 'ollama:main' into cors frob 2024-09-05 13:12:20 +02:00
  • da1de16e47 ... L 2024-09-05 17:01:07 +08:00