Commit Graph

  • 4e1ff6dcbb
    Merge pull request #3926 from dhiltgen/ci_fixes v0.1.33-rc2 Daniel Hiltgen 2024-04-25 17:42:31 -07:00
  • 8589d752ac Fix release CI Daniel Hiltgen 2024-04-25 17:27:11 -07:00
  • 030aee748f Load arrays in chunks Bryce Reitano 2024-04-25 18:13:04 -06:00
  • de4ded68b0
    Merge pull request #3923 from ollama/mxyng/mem v0.1.33-rc1 Michael Yang 2024-04-25 16:34:17 -07:00
  • 9b5a3c5991
    Merge pull request #3914 from dhiltgen/mac_perf Daniel Hiltgen 2024-04-25 16:28:31 -07:00
  • 00b0699c75
    Reload model if num_gpu changes (#3920) Jeffrey Morgan 2024-04-25 19:02:40 -04:00
  • 993cf8bf55
    llm: limit generation to 10x context size to avoid run on generations (#3918) Jeffrey Morgan 2024-04-25 19:02:30 -04:00
  • d25b42616d simplify condition statement jmorganca 2024-04-25 18:58:52 -04:00
  • 963404255e fix tests jmorganca 2024-04-25 18:51:55 -04:00
  • e2aeda4e0d dont reload on -1 jmorganca 2024-04-25 18:07:42 -04:00
  • 949f4b582f reload model if num_gpu changes jmorganca 2024-04-25 15:19:59 -04:00
  • 97d82fe12f add comment jmorganca 2024-04-25 18:42:28 -04:00
  • f553319cd1 llm: limit generation to 10x context size to avoid run on generations jmorganca 2024-04-25 14:19:41 -04:00
  • 7bb7cb8a60 only count output tensors Michael Yang 2024-04-25 14:41:50 -07:00
  • b123be5b71 Adjust context size for parallelism Daniel Hiltgen 2024-04-25 09:38:31 -07:00
  • ddf5c09a9b use matrix multiplcation kernels in more cases jmorganca 2024-04-25 00:33:33 -04:00
  • 5f73c08729
    Remove trailing spaces (#3889) Roy Yang 2024-04-25 11:32:26 -07:00
  • f503a848c2
    Merge pull request #3895 from brycereitano/shiftloading Daniel Hiltgen 2024-04-25 09:24:08 -07:00
  • 6fe760eded
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-25 11:53:12 +03:00
  • 27d88dbfdc use matrix multiplcation kernels in more cases jmorganca/mm jmorganca 2024-04-25 00:33:33 -04:00
  • c0314cc41c feed the linter pdevine/showggmlinfo Patrick Devine 2024-04-24 20:54:27 -07:00
  • 686178b6c5 show ggml modelinfo through the show api Patrick Devine 2024-04-24 18:53:00 -07:00
  • f37552c147 add information about compiling with intel mkl Kevin Hannon 2024-04-24 20:54:12 -04:00
  • 36a6daccab Restructure loading conditional chain Bryce Reitano 2024-04-24 17:37:03 -06:00
  • ceb0e26e5e Provide variable ggml for TestLoad Bryce Reitano 2024-04-24 17:19:55 -06:00
  • 284e02bed0 Move ggml loading to when we attempt fitting Bryce Reitano 2024-04-24 17:17:24 -06:00
  • 3450a57d4a
    Merge pull request #3713 from ollama/mxyng/modelname Michael Yang 2024-04-24 16:00:32 -07:00
  • 592dae31c8 update copy to use model.Name Michael Yang 2024-04-16 16:22:38 -07:00
  • 55ac7254a3 add param count tag to latest push by default brucemacd/default-param-tag Bruce MacDonald 2024-04-24 15:20:21 -07:00
  • 2010cbc5fa
    Merge pull request #3833 from ollama/mxyng/fix-from Michael Yang 2024-04-24 15:13:47 -07:00
  • 39a199bb3e remove duplicate check for ".." 1753720622133261720/tmp_refs/heads/modenameenforcealphanum 1753720622133261720/modenameenforcealphanum modenameenforcealphanum Blake Mizerany 2024-04-24 15:04:41 -07:00
  • ac0801eced only replace if it matches command Michael Yang 2024-04-24 14:27:12 -07:00
  • ad66e5b060 split temp zip files Michael Yang 2024-04-22 11:02:25 -07:00
  • 9221e04ae9 Remove trailing spaces Roy Yang 2024-04-24 19:57:52 +00:00
  • 1b21a22d0e types/model: require all names parts start with an alnum char bmizerany/modenameenforcealphanum Blake Mizerany 2024-04-24 11:49:56 -07:00
  • ade4b55520
    types/model: make ParseName use default without question (#3886) Blake Mizerany 2024-04-24 11:52:55 -07:00
  • 3e5a0df0e0 types/model: make ParseName use default without question Blake Mizerany 2024-04-24 11:30:20 -07:00
  • a6d62e0617
    Merge pull request #3882 from dhiltgen/amd_gfx Daniel Hiltgen 2024-04-24 11:07:49 -07:00
  • 6e76348df7
    Merge pull request #3834 from dhiltgen/not_found_in_path Daniel Hiltgen 2024-04-24 10:50:48 -07:00
  • 0d6687f84c AMD gfx patch rev is hex Daniel Hiltgen 2024-04-24 09:43:52 -07:00
  • 7d37625055 Update README.md Fernando Maclen 2024-04-24 12:39:39 -04:00
  • 947bf234e7
    Merge branch 'ollama:main' into http-bandwidth-limit Eren Aslan 2024-04-24 17:44:53 +03:00
  • abe154a4e6 Use ReadFull over CopyN when decoding GGUFs Bryce Reitano 2024-04-24 08:31:57 -06:00
  • bda93c8b85
    Merge pull request #3 from uppercaveman/uppercaveman-patch-1 clark 2024-04-24 17:10:15 +08:00
  • 8127925f18
    Update README.md clark 2024-04-24 17:09:20 +08:00
  • 7d627ecc76 fix bug chenbing 2024-04-24 13:06:15 +08:00
  • 7194a01b9f
    Merge pull request #2 from ollama/main clark 2024-04-24 12:57:01 +08:00
  • 9940f43cd6 Conform logging to surrounding implementation Self Denial 2024-04-23 22:25:06 -06:00
  • 74d2a9ef9a
    add OLLAMA_KEEP_ALIVE env variable to FAQ (#3865) Patrick Devine 2024-04-23 21:06:51 -07:00
  • 14476d48cc
    fixes for gguf (#3863) Patrick Devine 2024-04-23 20:57:20 -07:00
  • e23d0eb201 add OLLAMA_KEEP_ALIVE env variable to FAQ Patrick Devine 2024-04-23 20:56:38 -07:00
  • e5eb9d9be0 fixes for gguf Patrick Devine 2024-04-23 20:28:15 -07:00
  • 216c3604d5
    Merge branch 'ollama:main' into main Jim Scardelis 2024-04-23 20:18:07 -07:00
  • ce8ce82567
    add mixtral 8x7b model conversion (#3859) Patrick Devine 2024-04-23 20:17:04 -07:00
  • b8500eb337 delete workflows chenbing 2024-04-24 10:41:59 +08:00
  • dfdc6c7535 Merge branch 'ollama-main' chenbing 2024-04-24 10:36:00 +08:00
  • 533246443f fix conflict chenbing 2024-04-24 10:35:36 +08:00
  • 9fc80bcefa project theme chenbing 2024-04-24 09:39:27 +08:00
  • 4dc4f1be34
    types/model: restrict digest hash part to a minimum of 2 characters (#3858) Blake Mizerany 2024-04-23 18:24:17 -07:00
  • b160680595 use mistral's layer handler for attn layers Patrick Devine 2024-04-23 18:23:07 -07:00
  • 6ddfd4d743
    Merge branch 'main' into llm-threads-gpu-layers-env-override lainedfles 2024-04-23 19:18:47 -06:00
  • 7506f9a752 types/model: restrict digest hash part to a minimum of 2 characters Blake Mizerany 2024-04-23 16:34:16 -07:00
  • 16b52331a4
    Merge pull request #3857 from dhiltgen/mem_escape_valve Daniel Hiltgen 2024-04-23 17:32:24 -07:00
  • cfc4eb44cc add mixtral model conversion Patrick Devine 2024-04-23 17:32:06 -07:00
  • 5445aaa94e Add back memory escape valve Daniel Hiltgen 2024-04-23 17:09:02 -07:00
  • 2ac3dd6853
    Merge pull request #3850 from dhiltgen/windows_packaging Daniel Hiltgen 2024-04-23 16:35:20 -07:00
  • d8851cb7a0 Harden sched TestLoad Daniel Hiltgen 2024-04-23 13:07:16 -07:00
  • 058f6cd2cc Move nested payloads to installer and zip file on windows Daniel Hiltgen 2024-04-23 12:19:17 -07:00
  • ab58ec809e
    Merge pull request #2 from alley-team/json-grammar-enhance Климентий Титов 2024-04-24 01:23:22 +03:00
  • 9c1166a15d
    Improved JSON grammar Mark CDA 2024-04-24 01:22:30 +03:00
  • 5ab43beccc
    Merge pull request #1 from alley-team/cpu-only-docker Климентий Титов 2024-04-24 01:19:14 +03:00
  • 8fee10f32d
    Merge branch 'ollama:main' into cpu-only-docker Климентий Титов 2024-04-24 01:12:47 +03:00
  • dfd1626fbb
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-24 01:12:36 +03:00
  • 908e4790bc
    Update windows.md Quinten van Buul 2024-04-24 00:01:52 +02:00
  • 643f950ea0
    Merge remote-tracking branch 'upstream/main' Gamunu Balagalla 2024-04-24 02:04:44 +05:30
  • 00a173eb5c
    fix: update docker build script Gamunu Balagalla 2024-04-24 01:47:09 +05:30
  • 790cf34d17
    Merge pull request #3846 from dhiltgen/missing_runner Daniel Hiltgen 2024-04-23 13:14:12 -07:00
  • 928d844896
    adding phi-3 mini to readme Michael 2024-04-23 13:58:31 -04:00
  • 8d7bf34eb4
    Update linux.md Mohamed A. Fouad 2024-04-23 13:49:02 -04:00
  • 939d6a8606 Make CI lint verbvose Daniel Hiltgen 2024-04-23 10:17:42 -07:00
  • 8afcf883e4
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-23 20:16:05 +03:00
  • 58888a74bc Detect and recover if runner removed Daniel Hiltgen 2024-04-23 10:05:26 -07:00
  • cc5a71e0e3
    Merge pull request #3709 from remy415/custom-gpu-defs Daniel Hiltgen 2024-04-23 09:28:34 -07:00
  • e83bcf7f9a
    Merge pull request #3836 from ollama/mxyng/mixtral Michael Yang 2024-04-23 09:15:10 -07:00
  • f81828fc36
    Merge branch 'main' of github.com:alley-team/grammared-ollama Mark CDA 2024-04-23 18:43:39 +03:00
  • f4d224b8d8
    updated docs: added info about GBNF Mark CDA 2024-04-23 18:42:40 +03:00
  • 1d2617b816
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-23 18:32:02 +03:00
  • 5690e5ce99
    Merge pull request #3418 from dhiltgen/concurrency Daniel Hiltgen 2024-04-23 08:31:38 -07:00
  • bff7dce4ff add details on kubernetes deployment and separate the testing process QIN Mélony 2024-04-23 14:00:25 +02:00
  • 7b7cd254a5
    Merge pull request #1 from ollama/main Mélony QIN 2024-04-23 13:56:29 +02:00
  • 6188b5da44 adjusting project structure chenbing 2024-04-23 17:47:06 +08:00
  • 97c883bbc5
    Merge af30144cf3e5b317972e7d14244391ec1ce38c3e into ee448deaba0e5e74157c2bf1ba8408b340192a90 Alexandre Macabies 2024-04-23 10:42:35 +02:00
  • 2ea04b947b
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-23 08:26:29 +03:00
  • f2ea8470e5 Local unicode test case Daniel Hiltgen 2024-04-16 13:42:52 -07:00
  • 34b9db5afc Request and model concurrency Daniel Hiltgen 2024-03-30 09:50:05 -07:00
  • 8711d03df7 Report errors on server lookup instead of path lookup failure Daniel Hiltgen 2024-04-22 16:22:05 -07:00
  • ee448deaba
    Merge pull request #3835 from dhiltgen/harden_llm_override Daniel Hiltgen 2024-04-22 19:06:54 -07:00
  • 6e8db04716 tidy community integrations Bruce MacDonald 2024-04-22 17:29:08 -07:00
  • 658e60cf73 Revert "stop running model on interactive exit" Bruce MacDonald 2024-04-22 17:23:11 -07:00
  • 4c78f028f8 Merge branch 'main' of https://github.com/ollama/ollama Bruce MacDonald 2024-04-22 17:22:28 -07:00