Commit Graph

  • 6adca97f37
    Merge pull request #4619 from noxer/patch-1 Michael Yang 2024-05-24 17:21:57 -07:00
  • 9a3c8003c8
    Merge pull request #4624 from ollama/mxyng/fix-5 Michael Yang 2024-05-24 16:11:21 -07:00
  • d51f15257c
    Update llm/ggml.go Michael Yang 2024-05-24 16:10:43 -07:00
  • 8f440d579a fix q5_0, q5_1 Michael Yang 2024-05-24 16:01:37 -07:00
  • 4cc3be3035
    Move envconfig and consolidate env vars (#4608) Patrick Devine 2024-05-24 14:57:15 -07:00
  • 8880600c36
    Update README.md Rajat Paharia 2024-05-24 16:13:34 -05:00
  • 0177d32d01 Add explicit http scheme flag for registry Daniel Hiltgen 2024-05-24 12:36:36 -07:00
  • e0dfea5b6f added comments, refactored add function to use addChar Josh Yan 2024-05-24 12:30:31 -07:00
  • db2ffa79f1
    Fix download retry issue Tim Scheuermann 2024-05-24 20:30:42 +02:00
  • 1181b8a77b
    Merge branch 'ollama:main' into main richardanaya2_2048b.Q6_K.gguf 2024-05-24 11:09:06 -07:00
  • f12cd7f067 Allow https with insecure flag Daniel Hiltgen 2024-05-24 09:54:51 -07:00
  • 5ea057728e
    Added headless-ollama Nischal Jain 2024-05-24 19:26:08 +05:30
  • 8f0a44f293
    Merge 80c4806f28e295908df5b70da92073bd74343057 into afd2b058b4ee36230ab2a06927bdc0ff41b1e7ae Eric Curtin 2024-05-24 05:10:10 -04:00
  • 1b5fe3a34b Add truncation guard Eric Curtin 2024-05-24 08:57:32 +01:00
  • 5ee6d63f34 feed the linter Patrick Devine 2024-05-23 23:52:11 -07:00
  • 380783910d fix import Patrick Devine 2024-05-23 23:47:31 -07:00
  • e2137087e5 formatting Patrick Devine 2024-05-23 23:41:49 -07:00
  • d2be93aa1e consolidate env vars Patrick Devine 2024-05-23 23:38:57 -07:00
  • e6a5d2d0bb move envconfig Patrick Devine 2024-05-20 17:08:25 -07:00
  • afd2b058b4
    set codesign timeout to longer (#4605) Jeffrey Morgan 2024-05-23 22:46:23 -07:00
  • 4fc6a6b633 set codesign timeout to longer jmorganca 2024-05-23 22:45:19 -07:00
  • fd5971be0b support ollama run on Intel GPUs Wang,Zhe 2024-05-24 11:18:27 +08:00
  • 89bf98bcf2
    Merge pull request #4598 from dhiltgen/docs Daniel Hiltgen 2024-05-23 15:14:29 -07:00
  • 1b2d156094 Tidy up developer guide a little Daniel Hiltgen 2024-05-23 14:24:07 -07:00
  • 714adb8bd1
    bump (#4597) Michael Yang 2024-05-23 14:16:26 -07:00
  • 95b1133d0c
    Merge pull request #4547 from dhiltgen/load_progress Daniel Hiltgen 2024-05-23 14:06:02 -07:00
  • b37b496a12 Wire up load progress Daniel Hiltgen 2024-05-20 16:41:43 -07:00
  • d6f692ad1a
    Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) Bruce MacDonald 2024-05-23 13:21:49 -07:00
  • 643abf7ae8 Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL Bruce MacDonald 2024-05-23 12:18:42 -07:00
  • 7df09dd239 bump Michael Yang 2024-05-23 11:16:04 -07:00
  • 6d4d778b3c removed duplicate code Josh Yan 2024-05-23 10:26:59 -07:00
  • f77713bf1f Add isolated gpu test to troubleshooting Daniel Hiltgen 2024-05-23 09:33:25 -07:00
  • 38255d2af1
    Use flash attention flag for now (#4580) v0.1.39-rc2 Jeffrey Morgan 2024-05-22 21:52:09 -07:00
  • bd4ade58f9
    Add new community integration (TypingMind) Tony Dinh 2024-05-23 12:31:27 +08:00
  • b537fc5ee5 deleted comments and duplicate code Josh Yan 2024-05-22 18:00:27 -07:00
  • 013b20128c
    Update readline/buffer.go Josh 2024-05-22 17:30:18 -07:00
  • 931d29b4a0
    Update readline/buffer.go Josh 2024-05-22 17:29:43 -07:00
  • ff0722d673
    Update readline/buffer.go Josh 2024-05-22 17:29:25 -07:00
  • 3aa3690a7e
    Update readline/buffer.go Josh 2024-05-22 17:29:04 -07:00
  • 48f379ae22
    Update readline/buffer.go Josh 2024-05-22 17:28:48 -07:00
  • cd763d7a79
    Update readline/buffer.go Josh 2024-05-22 17:28:06 -07:00
  • 19b23626e4
    Update readline/buffer.go Josh 2024-05-22 17:27:47 -07:00
  • 398a0bc4ec
    Update readline/buffer.go Josh 2024-05-22 17:27:39 -07:00
  • b0571190cc
    Update readline/buffer.go Josh 2024-05-22 17:27:19 -07:00
  • 5a8aff3a61
    Update readline/buffer.go Josh 2024-05-22 17:25:38 -07:00
  • 9969b90e55
    Update readline/buffer.go Josh 2024-05-22 17:25:30 -07:00
  • db5477a0bb
    Update readline/buffer.go Josh 2024-05-22 17:25:17 -07:00
  • 6ed217b764 DO NOT MERGE - testing CI Daniel Hiltgen 2024-05-22 16:50:06 -07:00
  • cdaa4e7feb up timeout for sheduler tests jmorganca 2024-05-22 16:42:40 -07:00
  • 7b7ea4fb5e remove print jmorganca 2024-05-22 16:17:56 -07:00
  • f296bd80ef add test jmorganca 2024-05-22 16:17:26 -07:00
  • abe0dbd71e put flash attention behind flag for now jmorganca 2024-05-22 16:16:50 -07:00
  • 73630a7e85
    add phi 3 medium (#4578) Michael 2024-05-22 12:53:45 -04:00
  • 2f59384bd0
    add phi 3 medium Michael 2024-05-22 12:53:01 -04:00
  • 3d7cd8121e feat: add support for min_p (resolve #1142) Tibor Schmidt 2024-05-09 06:49:48 +02:00
  • 955c317cab
    chore: update tokenizer.go (#4571) Ikko Eltociear Ashimine 2024-05-22 16:25:23 +09:00
  • 509fac932f
    chore: update tokenizer.go Ikko Eltociear Ashimine 2024-05-22 15:47:32 +09:00
  • 9f18b88a06
    Merge pull request #4566 from ollama/jyan/shortcuts Josh 2024-05-21 22:49:36 -07:00
  • eaf0993b5b merge code chenbing 2024-05-22 11:03:41 +08:00
  • 353f83a9c7 add Ctrl + W shortcut Josh Yan 2024-05-21 16:55:09 -07:00
  • 45ead201cc
    Merge 36dc001cbfcc9f20791db6a8c03f9ed29729e4dc into 3bade04e10fae0db1b0a62ec0d5d9883a6f3c3bf Guofeng Yi 2024-05-21 18:33:58 -05:00
  • 1441bd607b removed comments Josh Yan 2024-05-21 15:49:12 -07:00
  • 3bade04e10
    doc updates for the faq/troubleshooting (#4565) Patrick Devine 2024-05-21 15:30:09 -07:00
  • f298c60d90 adjusted hotkeys Josh Yan 2024-05-21 15:19:59 -07:00
  • 4ed252afd6 fixed movement hotkeys Josh Yan 2024-05-21 15:09:10 -07:00
  • 8cec7ee670 fixed minor inserting bug Josh Yan 2024-05-21 14:57:52 -07:00
  • 4996d064cb add ollama ps faq Patrick Devine 2024-05-21 14:53:58 -07:00
  • a6d0f443eb
    Merge pull request #4543 from ollama/mxyng/simple-safetensors v0.1.39-rc1 Michael Yang 2024-05-21 14:43:55 -07:00
  • 96236b7968
    Merge pull request #4268 from ollama/pdevine/llama3 Michael Yang 2024-05-21 14:43:37 -07:00
  • e9dca18b89 fixed failed test Josh Yan 2024-05-21 14:41:33 -07:00
  • ed17a2c571 worked on end of line Josh Yan 2024-05-21 14:36:54 -07:00
  • 4434d7f447
    Correct typo in error message (#4535) Sang Park 2024-05-22 05:39:01 +09:00
  • bd3dcf2a5f update the faq / troubleshooting guides for style/formatting Patrick Devine 2024-05-21 13:26:13 -07:00
  • 171eb040fc simplify safetensors reading Michael Yang 2024-05-20 09:47:01 -07:00
  • 3591bbe56f add test Michael Yang 2024-05-21 11:28:16 -07:00
  • 34d5ef29b3 fix conversion for f16 or f32 inputs Michael Yang 2024-05-17 12:11:49 -07:00
  • 2ff004b4a9
    added healthcheck to all runtime stages joecryptotoo 2024-05-20 19:43:36 -07:00
  • 237e8d8767 Fix a typo in server/sched.go Lei Jitang 2024-05-21 10:00:02 +08:00
  • fed24d8406 worked some more Josh Yan 2024-05-20 17:23:22 -07:00
  • 46ca19c057
    Merge 7710d949dd7bd811f5b6437988a60b06a2d65080 into 2f81b3dce24c77030d5e45a34b4f0c747d79067b Rene Leonhardt 2024-05-21 09:14:50 +10:00
  • bbbd9f20f3 cleanup Michael Yang 2024-05-15 14:55:57 -07:00
  • 547132e820 bpe pretokenizer Michael Yang 2024-05-15 11:53:14 -07:00
  • 2d315ba9a9 add missing file Patrick Devine 2024-05-08 16:56:18 -07:00
  • d355d2020f add fixes for llama Patrick Devine 2024-05-08 16:07:46 -07:00
  • c8cf0d94ed llama3 conversion Patrick Devine 2024-04-28 10:36:38 -07:00
  • 4730762e5c add safetensors version Patrick Devine 2024-04-24 18:32:01 -07:00
  • d88582dffd some changes for llama3 Patrick Devine 2024-04-18 16:00:20 -07:00
  • 2f81b3dce2
    Merge pull request #4502 from ollama/mxyng/fix-quantize Michael Yang 2024-05-20 16:09:27 -07:00
  • 5cab13739e set llama.cpp submodule commit to 614d3b9 jmorganca 2024-05-20 15:28:17 -07:00
  • 8aadad9c72 updated updateURL Josh Yan 2024-05-20 15:24:32 -07:00
  • 807d092761 fix quantize file types Michael Yang 2024-05-17 11:29:04 -07:00
  • f36f1d6be9 tidy intermediate blobs Michael Yang 2024-05-20 14:58:27 -07:00
  • 2841395af9 fixed end of line issues with empty spaces Josh Yan 2024-05-20 15:00:17 -07:00
  • 8800c8a59b
    chore: fix typo in docs (#4536) alwqx 2024-05-21 05:19:03 +08:00
  • d6e6b427a8 saved changes Josh Yan 2024-05-20 14:12:01 -07:00
  • ce681efb0f end of line extra space tracking' Josh Yan 2024-05-20 14:11:36 -07:00
  • 2731b7854b fixed issues with moving across lines Josh Yan 2024-05-20 14:03:51 -07:00
  • b4dce13309
    Merge pull request #4330 from ollama/mxyng/cache-intermediate-layers Michael Yang 2024-05-20 13:54:41 -07:00
  • e15307fdf4
    feat: add support for flash_attn (#4120) Sam 2024-05-21 06:36:03 +10:00
  • 3520c0e4d5 cache and reuse intermediate blobs Michael Yang 2024-05-10 15:48:41 -07:00