Commit Graph

  • 7ca71a6b0f
    don't abort when an invalid model name is used in /save (#4416) Patrick Devine 2024-05-13 18:48:28 -07:00
  • 2a1fa7c3b7 don't abort when an invalid model name is used in /save Patrick Devine 2024-05-13 18:40:16 -07:00
  • 7607e6e902
    Merge pull request #4379 from WolfTheDeveloper/main Josh 2024-05-13 18:08:32 -07:00
  • f1548ef62d
    update the FAQ to be more clear about windows env variables (#4415) Patrick Devine 2024-05-13 18:01:13 -07:00
  • fde7159f12 update the FAQ to be more clear about windows env variables Patrick Devine 2024-05-13 17:58:11 -07:00
  • 6845988807
    Ollama ps command for showing currently loaded models (#4327) Patrick Devine 2024-05-13 17:17:36 -07:00
  • e857112f4d update llama.cpp submodule to 614d3b9 jmorganca 2024-05-13 16:17:21 -07:00
  • 9eed4a90ce
    Merge pull request #4411 from joshyan1/main Josh 2024-05-13 15:30:45 -07:00
  • f8464785a6 removed inconsistencies Josh Yan 2024-05-13 14:50:52 -07:00
  • d7536da0bc
    Merge 980070dce6e6d98aa883f8d519e76ce602066897 into af11838245c125de9208e53b23e2e5fddcfeb045 Michael Yang 2024-05-13 21:25:44 +00:00
  • 980070dce6 remove last bits of ParseModelPath mxyng/modelname-8 Michael Yang 2024-05-08 18:02:07 -07:00
  • af11838245 update push to use model.Name Michael Yang 2024-05-08 17:34:54 -07:00
  • 7cb2fd3555 fix(server): prune files Michael Yang 2024-05-08 15:53:38 -07:00
  • 0aeaeaa058 update pull handler to use model.Name Michael Yang 2024-05-08 15:08:29 -07:00
  • 1d359e737e typo Michael Yang 2024-05-13 14:14:10 -07:00
  • 50b9056e09 count memory up to NumGPU Michael Yang 2024-05-10 14:40:37 -07:00
  • 91a090a485 removed inconsistent punctuation Josh Yan 2024-05-13 14:08:22 -07:00
  • b91cf0893d update create handler to use model.Name Michael Yang 2024-05-08 14:36:08 -07:00
  • 8215545c6d more resilient Manifests Michael Yang 2024-05-09 10:00:18 -07:00
  • 34a1dbe6ec filepath.Join Michael Yang 2024-05-08 15:56:40 -07:00
  • 6f2a09abfd remove DeleteModel Michael Yang 2024-05-08 14:54:52 -07:00
  • 14f9dc4e6a routes: use Manifests for ListHandler Michael Yang 2024-05-06 16:34:13 -07:00
  • eeba2cbae3 update delete handler to use model.Name Michael Yang 2024-04-17 17:23:19 -07:00
  • 4608c5ed1f update llama.cpp submodule to support jina embeddings v2 Joan Martinez 2024-05-13 13:56:08 +02:00
  • 95a9152d01
    Merge 87c3e61a0aec67abffc322e5787df463a485ddb3 into 9c76b30d72b76f0ce1fe7f357651ea9985c2cb24 kaizau 2024-05-13 14:37:37 +03:00
  • 8aea5f1dc1 fix embedding by adding fixes from llama.cpp upstream Jesper Ek 2024-05-13 13:09:12 +02:00
  • 9c76b30d72
    Correct typos. (#4387) 睡觉型学渣 2024-05-13 09:21:11 +08:00
  • 348ee10fc2 Correct typos. fangtaosong 2024-05-13 08:02:13 +08:00
  • ff67802652 Correct typos. fangtaosong 2024-05-13 08:00:36 +08:00
  • e1f383437e Allow XDG user directories Noah Gitsham 2024-05-12 20:41:57 +01:00
  • 93f19910c5
    Update LlamaScript to point to new link. Zander Lewis 2024-05-12 11:24:21 -04:00
  • a39ad71270 Create separate types for CompletionProbability / CompletionProbs -> more DRY code Markus 2024-05-12 13:24:16 +02:00
  • defec9ccfa Merge remote-tracking branch 'origin/main' Markus 2024-05-12 12:59:48 +02:00
  • 4ec7445a6f Revert "use post token" jmorganca 2024-05-11 22:19:14 -07:00
  • 7a9e2d678e
    Merge branch 'main' into gin Bo-Yi Wu 2024-05-12 12:32:18 +08:00
  • 0372c51f82
    Merge pull request #4369 from ollama/mxyng/post-token Michael Yang 2024-05-11 19:29:14 -07:00
  • 0fec3525ad use post token Michael Yang 2024-05-11 19:13:16 -07:00
  • 41ba3017fd
    Fix OpenAI finish_reason values when empty (#4368) v0.1.37 Jeffrey Morgan 2024-05-11 15:31:41 -07:00
  • 7a1f75edf1 simpler approach jmorganca 2024-05-11 15:29:14 -07:00
  • 2f4b6d9636 finish_reason should be null if empty jmorganca 2024-05-11 15:27:05 -07:00
  • 2827f8bcfa openai: dont render empty finish_reason jmorganca 2024-05-11 15:19:30 -07:00
  • 8080fbce35
    fix ollama create's usage string (#4362) todashuta 2024-05-12 06:47:49 +09:00
  • abdf8e687e openai: dont render empty finish_reason jmorganca 2024-05-11 14:41:40 -07:00
  • ec14f6ceda
    case sensitive filepaths (#4366) Michael Yang 2024-05-11 14:12:36 -07:00
  • a53df8f8b3 case sensitive filepaths Michael Yang 2024-05-11 13:50:51 -07:00
  • 29e2adfef7 Install rocm packages on host system on dnf based system Eric Curtin 2024-05-11 15:29:13 +01:00
  • c60a086635
    Merge pull request #4331 from dhiltgen/fix_unit Daniel Hiltgen 2024-05-11 09:16:28 -07:00
  • f3606ce6e8
    fix ollama create's usage string todashuta 2024-05-11 23:01:48 +09:00
  • 451afd1e65 Server: refactor parsing model configuration Redouan El Rhazouani 2024-05-11 13:13:56 +02:00
  • 92ca2cca95 Revert "only forward some env vars" v0.1.36 jmorganca 2024-05-10 22:53:21 -07:00
  • 1e1634daca
    update go deps (#4324) Patrick Devine 2024-05-10 21:39:27 -07:00
  • ddef11f87e update more deps Patrick Devine 2024-05-10 21:24:27 -07:00
  • 5f1a713273 update gin Patrick Devine 2024-05-10 20:55:54 -07:00
  • 9f3c04508a add back the toolchain Patrick Devine 2024-05-10 20:53:10 -07:00
  • 30e4579f08
    chore: update dependencies across the board Bo-Yi Wu 2024-05-11 11:19:19 +08:00
  • 824ee5446f Fix envconfig unit test Daniel Hiltgen 2024-05-10 16:49:48 -07:00
  • d94da46c09 feed the linter Patrick Devine 2024-05-10 16:39:23 -07:00
  • bc03ad8156 fix sched unit tests Patrick Devine 2024-05-10 16:33:29 -07:00
  • 879e2caf8c
    Merge pull request #4329 from dhiltgen/zero_layers Daniel Hiltgen 2024-05-10 15:23:16 -07:00
  • c4014e73a2 Fall back to CPU runner with zero layers Daniel Hiltgen 2024-05-10 15:09:48 -07:00
  • be9efdb981
    Merge pull request #4326 from dhiltgen/fix_integration Daniel Hiltgen 2024-05-10 14:25:59 -07:00
  • 074dc3b9d8 Integration fixes Daniel Hiltgen 2024-05-10 14:13:26 -07:00
  • dd38c7e8e9 show cpu/gpu percentages Patrick Devine 2024-05-09 21:51:03 -07:00
  • a8e6033168 add keepalive to ollama run Patrick Devine 2024-05-08 18:34:45 -07:00
  • 334fdc7366 humantime forever Patrick Devine 2024-05-05 14:37:23 -07:00
  • 8d95c9bc91 add ollama ps command Patrick Devine 2024-05-05 11:50:28 -07:00
  • 86f9b582d5
    Merge pull request #4323 from dhiltgen/sort_by_free v0.1.35 Daniel Hiltgen 2024-05-10 14:12:15 -07:00
  • c162965f0a update go deps Patrick Devine 2024-05-10 14:04:31 -07:00
  • 4142c3ef7c Always use the sorted list of GPUs Daniel Hiltgen 2024-05-10 13:53:21 -07:00
  • b1baa86f34
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-10 23:38:33 +03:00
  • 6602e793c0
    Use --quantize flag and quantize api parameter (#4321) Jeffrey Morgan 2024-05-10 13:06:13 -07:00
  • 6bed6f290c
    Update api/types.go Jeffrey Morgan 2024-05-10 12:57:38 -07:00
  • ea0fdaed28
    Merge pull request #4320 from ollama/mxyng/phi2-mem Michael Yang 2024-05-10 12:35:08 -07:00
  • e6fe6517df backwards jmorganca 2024-05-10 12:19:27 -07:00
  • 1eb382da5a add phi2 mem Michael Yang 2024-05-10 12:13:28 -07:00
  • bb6fd02298
    Don't clamp ctx size in PredictServerFit (#4317) Jeffrey Morgan 2024-05-10 10:17:12 -07:00
  • 938be81c45 Add TODO brucemacd/tokenize Bruce MacDonald 2024-05-10 10:15:22 -07:00
  • 19ce10e49e add a /tokenize endpoint Bruce MacDonald 2024-05-01 20:14:32 -07:00
  • 2cb2e8a4fa
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-10 20:13:06 +03:00
  • 7e2bceceee
    Merge pull request #4316 from dhiltgen/more_buffer Daniel Hiltgen 2024-05-10 10:02:34 -07:00
  • ad56fcaf12 remove context warning jmorganca 2024-05-10 09:44:40 -07:00
  • 8ed37e6657 minimum 4 context jmorganca 2024-05-10 09:39:22 -07:00
  • 781fbe230b dont clamp ctx size in PredictServerFit jmorganca 2024-05-10 09:32:41 -07:00
  • 30a7d7096c Bump VRAM buffer back up Daniel Hiltgen 2024-05-10 09:15:28 -07:00
  • 255d01166c rename --quantization to --quantize jmorganca 2024-05-10 09:01:33 -07:00
  • 200a18820e
    Merge pull request #4306 from ollama/mxyng/fix-routes Michael Yang 2024-05-10 08:58:16 -07:00
  • e03637176d fix(routes): skip bad manifests Michael Yang 2024-05-09 17:44:34 -07:00
  • 84da3a3916 add ollama-operator in example Peter Pan 2024-05-10 16:03:34 +08:00
  • 8ba68c7595
    Merge branch 'main' into main josc146 2024-05-10 12:09:17 +08:00
  • c02db93243 omit empty done reason v0.1.35-rc1 Bruce MacDonald 2024-05-09 16:45:29 -07:00
  • ffa4d5134a
    Merge pull request #4305 from ollama/mxyng/typo Michael Yang 2024-05-09 16:42:09 -07:00
  • 6ff5d987e1
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-10 02:36:05 +03:00
  • 302d7fdbf3
    prune partial downloads (#4272) Jeffrey Morgan 2024-05-09 16:35:20 -07:00
  • fa75f360f1 prune partial downloads jmorganca 2024-05-08 18:45:56 -07:00
  • cf442cd57e fix typo Michael Yang 2024-05-09 16:23:37 -07:00
  • 0e1ba65855
    Merge pull request #4302 from ollama/mxyng/forward-env Michael Yang 2024-05-09 16:21:05 -07:00
  • 6aad333c63
    Merge pull request #4298 from ollama/mxyng/log-cleanup Michael Yang 2024-05-09 16:20:57 -07:00
  • a9627c8135
    Update README.md Dezoito 2024-05-09 20:01:29 -03:00
  • 4fcc84e67a
    Merge pull request #4304 from dhiltgen/signals Daniel Hiltgen 2024-05-09 15:58:44 -07:00
  • 3ae2f441e0 Fix race in shutdown logic Daniel Hiltgen 2024-05-09 15:47:02 -07:00