Commit graph

Select branches

Hide pull requests

master

Mono Color

• aa72281eae Trim spaces and quotes from llm lib override Daniel Hiltgen 2024-04-22 17:11:14 -07:00
• 74bcbf828f
  add qa-pilot link (#3612) reid41 2024-04-23 08:10:34 +08:00
• fe39147e64
  Add Chatbot UI v2 to Community Integrations (#3503) Christian Neff 2024-04-23 02:09:55 +02:00
• fad00a85e5 stop running model on interactive exit Bruce MacDonald 2024-04-22 16:22:14 -07:00
• 9c0db4cc83
  Update gen_windows.ps1 Jeremy 2024-04-21 16:13:41 -04:00
• 62be2050dd
  chore: use errors.New to replace fmt.Errorf will much better (#3789) Cheng 2024-04-21 10:11:06 +08:00
• 56f8aa6912
  types/model: export IsValidNamePart (#3788) Blake Mizerany 2024-04-20 18:26:34 -07:00
• e6f9bfc0e8
  Update api.md (#3705) Sri Siddhaarth 2024-04-21 00:47:03 +05:30
• 6f18297b3a
  Update gen_windows.ps1 Jeremy 2024-04-18 19:47:44 -04:00
• 15016413de
  Update gen_windows.ps1 Jeremy 2024-04-18 19:27:16 -04:00
• 440b7190ed
  Update gen_linux.sh Jeremy 2024-04-18 19:18:10 -04:00
• 8d1995c625
  Merge pull request #3708 from remy415/arm64static Daniel Hiltgen 2024-04-18 16:04:12 -07:00
• fd01fbf038
  Merge pull request #3710 from remy415/update-jetson-docs Daniel Hiltgen 2024-04-18 16:02:08 -07:00
• 0408205c1c
  types/model: accept former : as a separator in digest (#3724) Blake Mizerany 2024-04-18 14:17:46 -07:00
• 63a7edd771
  Update README.md Jeffrey Morgan 2024-04-18 16:09:38 -04:00
• 554ffdcce3
  add llama3 to readme Michael 2024-04-18 15:18:48 -04:00
• c496967e56
  Merge branch 'ollama:main' into mannix-server ManniX-ITA 2024-04-18 18:45:15 +02:00
• 9850a4ce08
  Merge branch 'ollama:main' into update-jetson-docs Jeremy 2024-04-18 09:55:17 -04:00
• 3934c15895
  Merge branch 'ollama:main' into custom-gpu-defs Jeremy 2024-04-18 09:55:10 -04:00
• fd048f1367
  Merge branch 'ollama:main' into arm64static Jeremy 2024-04-18 09:55:04 -04:00
• 8645076a71
  Merge pull request #3712 from ollama/mxyng/mem Michael Yang 2024-04-17 15:57:51 -07:00
• 05e9424824
  Merge pull request #3664 from ollama/mxyng/fix-padding-2 Michael Yang 2024-04-17 15:57:40 -07:00
• 52ebe67a98
  Merge pull request #3714 from ollama/mxyng/model-name-host Michael Yang 2024-04-17 15:34:03 -07:00
• 889b31ab78 types/model: support : in PartHost for host:port Michael Yang 2024-04-17 15:13:05 -07:00
• 3cf483fe48 add stablelm graph calculation Michael Yang 2024-04-17 13:57:19 -07:00
• 8dca03173d Merge remote-tracking branch 'upstream/main' into update-jetson-docs Jeremy 2024-04-17 16:18:50 -04:00
• 85bdf14b56 update jetson tutorial Jeremy 2024-04-17 16:17:42 -04:00
• d524e5ef5e Merge branch 'custom-gpu-defs' of https://github.com/remy415/ollama into custom-gpu-defs Jeremy 2024-04-17 16:01:03 -04:00
• 52f5370c48 add support for custom gpu build flags for llama.cpp Jeremy 2024-04-17 16:00:48 -04:00
• da8a0c7657
  Merge branch 'ollama:main' into arm64static Jeremy 2024-04-17 15:22:34 -04:00
• 1b42b4b59a
  Merge branch 'ollama:main' into custom-gpu-defs Jeremy 2024-04-17 15:21:56 -04:00
• 7c000ec3ed adds support for OLLAMA_CUSTOM_GPU_DEFS to customize GPU build flags Jeremy 2024-04-17 15:21:05 -04:00
• c8afe7168c use correct extension for feature and model request issue templates jmorganca 2024-04-17 15:18:36 -04:00
• 28d3cd0148 simpler feature and model request forms jmorganca 2024-04-17 15:17:08 -04:00
• eb5554232a simpler feature and model request forms jmorganca 2024-04-17 15:14:49 -04:00
• ea4c284a48
  Merge branch 'ollama:main' into arm64static Jeremy 2024-04-17 15:11:38 -04:00
• 2bdc320216 add descriptions to issue templates jmorganca 2024-04-17 15:08:36 -04:00
• 32561aed09 simplify github issue templates a bit jmorganca 2024-04-17 15:06:57 -04:00
• 71548d9829
  Merge pull request #3706 from ollama/mxyng/mem Michael Yang 2024-04-17 11:58:20 -07:00
• 8aec92fa6d rearranged conditional logic for static build, dockerfile updated Jeremy 2024-04-17 14:43:28 -04:00
• a8b9b930b4 account for all non-repeating layers Michael Yang 2024-04-17 10:29:12 -07:00
• 9755cf9173
  acknowledge the amazing work done by Georgi and team! Michael 2024-04-17 13:48:14 -04:00
• 70261b9bb6 move static build to its own flag Jeremy 2024-04-17 13:04:28 -04:00
• c942e4a07b
  Fixed startup sequence to report model loading ManniX-ITA 2024-04-17 17:40:32 +02:00
• bd54b08261
  Streamlined WaitUntilRunning ManniX-ITA 2024-04-17 17:39:52 +02:00
• 9df6c85c3a
  types/model: add FilepathNoBuild (#3680) Blake Mizerany 2024-04-16 18:35:43 -07:00
• e74163af4c fix padding to only return padding Michael Yang 2024-04-15 17:31:11 -07:00
• fb9580df85
  Merge pull request #3684 from ollama/mxyng/scale-graph Michael Yang 2024-04-16 14:57:09 -07:00
• 26df674785 scale graph based on gpu count Michael Yang 2024-04-16 14:44:13 -07:00
• 7c9792a6e0
  Support unicode characters in model path (#3681) Jeffrey Morgan 2024-04-16 17:00:12 -04:00
• 7afb2e125a
  Merge pull request #3678 from ollama/mxyng/fix-darwin-partial-offloading Michael Yang 2024-04-16 12:05:56 -07:00
• 41a272de9f darwin: no partial offloading if required memory greater than system Michael Yang 2024-04-16 11:22:38 -07:00
• f335722275
  update llama.cpp submodule to 7593639 (#3665) Jeffrey Morgan 2024-04-15 23:04:43 -04:00
• 6d53b67c2c
  Merge pull request #3663 from ollama/mxyng/fix-padding Michael Yang 2024-04-15 17:44:54 -07:00
• 969238b19e fix padding in decode Michael Yang 2024-04-15 17:26:59 -07:00
• 949d7832cf
  Revert "cmd: provide feedback if OLLAMA_MODELS is set on non-serve command (#3470)" (#3662) Blake Mizerany 2024-04-15 16:58:00 -07:00
• 99d227c9db
  Added Solar example at README.md (#3610) Sung Kim 2024-04-15 16:54:23 -07:00
• a27e419b47
  Update langchainjs.md (#2030) Carlos Gamez 2024-04-16 06:37:30 +08:00
• e4d0db5a97
  Added MindsDB information (#3595) Chandre Van Der Westhuizen 2024-04-16 00:35:29 +02:00
• ba460802c2
  examples: add more Go examples using the API (#3599) Eli Bendersky 2024-04-15 15:34:54 -07:00
• e54a3c7fcd
  Update modelfile.md Jeffrey Morgan 2024-04-15 15:35:44 -04:00
• 9f8691c6c8
  Add llama2 / torch models for ollama create (#3607) Patrick Devine 2024-04-15 11:26:42 -07:00
• a0b8a32eb4
  Terminate subprocess if receiving SIGINT or SIGTERM signals while model is loading (#3653) Jeffrey Morgan 2024-04-15 12:09:32 -04:00
• 7027f264fb
  app: gracefully shut down ollama serve on windows (#3641) Jeffrey Morgan 2024-04-14 18:33:25 -04:00
• 9bee3b63b1
  types/model: add path helpers (#3619) Blake Mizerany 2024-04-13 12:59:19 -07:00
• 309aef7fee
  update llama.cpp submodule to 4bd0f93 (#3627) Jeffrey Morgan 2024-04-13 10:43:02 -07:00
• 08655170aa
  types/model: make ParseName variants less confusing (#3617) Blake Mizerany 2024-04-12 13:57:57 -07:00
• 2b341069a7
  types/model: remove (*Digest).Scan and Digest.Value (#3605) Blake Mizerany 2024-04-11 13:32:31 -07:00
• c00fee6936
  Merge pull request #3604 from dhiltgen/fix_rocm_deps Daniel Hiltgen 2024-04-11 13:08:29 -07:00
• c2d813bdc3 Fix rocm deps with new subprocess paths Daniel Hiltgen 2024-04-11 12:52:06 -07:00
• 786f3a1c44
  Merge pull request #3600 from ollama/mxyng/mixtral Michael Yang 2024-04-11 12:23:37 -07:00
• 3397eff0cd mixtral mem Michael Yang 2024-04-11 10:26:35 -07:00
• 0efb7931c7 Revert "types/model: remove (*Digest).Scan and Digest.Value (#3589)" Blake Mizerany 2024-04-11 00:45:07 -07:00
• 42f2cc408e
  types/model: remove (*Digest).Scan and Digest.Value (#3589) Blake Mizerany 2024-04-11 00:37:26 -07:00
• 9446b795b5
  types/model: remove DisplayLong (#3587) Blake Mizerany 2024-04-10 16:55:12 -07:00
• 62f8cda3b3
  types/model: remove MarshalText/UnmarshalText from Digest (#3586) Blake Mizerany 2024-04-10 16:52:49 -07:00
• 6a1de23175
  types/model: init with Name and Digest types (#3541) Blake Mizerany 2024-04-10 16:30:05 -07:00
• a7b431e743
  server: provide helpful workaround hint when stalling on pull (#3584) Blake Mizerany 2024-04-10 16:24:37 -07:00
• 5a25f93522
  Merge pull request #3478 from ollama/mxyng/tensor-layer Michael Yang 2024-04-10 12:45:03 -07:00
• 7e33a017c0 partial offloading Michael Yang 2024-04-05 14:50:38 -07:00
• 8b2c10061c refactor tensor query Michael Yang 2024-04-03 15:00:31 -07:00
• c5c451ca3b
  Merge pull request #3579 from ollama/mxyng/fix-ci Michael Yang 2024-04-10 11:37:01 -07:00
• 2b4ca6cf36 fix ci Michael Yang 2024-04-10 11:26:15 -07:00
• ad90b9ab3d
  api: start adding documentation to package api (#2878) Eli Bendersky 2024-04-10 10:31:55 -07:00
• 4340f8eba4
  examples: start adding Go examples using api/ (#2879) Eli Bendersky 2024-04-10 10:26:45 -07:00
• 4c7db6b7e9
  Merge pull request #3566 from dhiltgen/more_time Daniel Hiltgen 2024-04-09 16:53:49 -07:00
• c03f0e3c3d
  Merge pull request #3565 from ollama/mxyng/rope Michael Yang 2024-04-09 16:36:55 -07:00
• c5ff443b9f Handle very slow model loads Daniel Hiltgen 2024-04-09 16:35:10 -07:00
• 01114b4526 fix: rope Michael Yang 2024-04-09 16:15:24 -07:00
• 1524f323a3
  Revert "build.go: introduce a friendlier way to build Ollama (#3548)" (#3564) Blake Mizerany 2024-04-09 15:57:45 -07:00
• fccf3eecaa
  build.go: introduce a friendlier way to build Ollama (#3548) Blake Mizerany 2024-04-09 14:18:47 -07:00
• c77d45d836
  Merge pull request #3506 from ollama/mxyng/quantize-redux Michael Yang 2024-04-09 12:32:53 -07:00
• 5ec12cec6c
  update llama.cpp submodule to 1b67731 (#3561) Jeffrey Morgan 2024-04-09 15:10:17 -04:00
• d9578d2bad
  Merge pull request #3559 from ollama/mxyng/ci Michael Yang 2024-04-09 11:03:18 -07:00
• cb8352d6b4 ci: use go-version-file Michael Yang 2024-04-09 09:50:12 -07:00
• fc6558f47f
  Correct directory reference in macapp/README (#3555) Alex Mavrogiannis 2024-04-09 16:48:46 +03:00
• 9502e5661f cgo quantize Michael Yang 2024-04-05 08:49:04 -07:00
• e1c9a2a00f no blob create if already exists Michael Yang 2024-04-05 09:30:09 -07:00
• 1341ee1b56
  Update README.md (#3539) writinwaters 2024-04-08 22:58:14 +08:00
• 63efa075a0
  update generate scripts with new LLAMA_CUDA variable, set HIP_PLATFORM to avoid compiler errors (#3528) Jeffrey Morgan 2024-04-07 16:29:51 -07:00