Commit Graph

  • 1909e624ce update tests Michael Yang 2024-04-16 15:37:28 -07:00
  • 1d8c850f38 quantize any fp16/fp32 model Michael Yang 2024-04-12 13:55:12 -07:00
  • e9ae607ece
    Merge pull request #3892 from ollama/mxyng/parser Michael Yang 2024-05-02 17:04:47 -07:00
  • c852bca759
    Update import.md Kim Hallberg 2024-05-03 01:15:16 +02:00
  • 9ab74f1501
    Update import.md Kim Hallberg 2024-05-03 01:14:17 +02:00
  • 93707fa3f2
    Merge pull request #4108 from ollama/mxyng/lf Michael Yang 2024-05-02 14:55:15 -07:00
  • 94c369095f fix line ending Michael Yang 2024-05-02 14:52:21 -07:00
  • 11bcc40472 Add env variable OLLAMA_LOAD_TIMEOUT in seconds David Carreto Fidalgo 2024-05-02 23:32:13 +02:00
  • 415eb2c65b
    Fix for Nvidia installed deps detection algorithm in gpu.go alecvern 2024-05-02 22:44:08 +03:00
  • 9164b0161b
    Update .gitattributes v0.1.33 Jeffrey Morgan 2024-05-02 14:06:31 -04:00
  • c07913a002
    Update examples/kubernetes/README.md Mélony QIN 2024-05-02 09:40:58 +02:00
  • 7e79f59540 Merge branch 'ollama-main' chenbing 2024-05-02 08:38:50 +08:00
  • e869ad6dac merge code chenbing 2024-05-02 08:37:52 +08:00
  • 889c5b1a75 ... 1753720551637136648/tmp_refs/heads/bmizerany/client-registry 1753720551637136648/bmizerany/client-registry bmizerany/client-registry Blake Mizerany 2024-05-01 15:56:59 -07:00
  • e592e8fccb Support Fedoras standard ROCm location Daniel Hiltgen 2024-05-01 15:47:12 -07:00
  • 844217bcf1 weaving in Blake Mizerany 2024-05-01 15:32:24 -07:00
  • bf4fc25f7b
    Add a /clear command (#3947) Bryce Reitano 2024-05-01 15:44:36 -06:00
  • 7fbd63f33b change help messages Patrick Devine 2024-05-01 17:36:42 -04:00
  • 5b806d8d24
    Merge pull request #4089 from ollama/mxyng/target-invalid v0.1.33-rc7 Michael Yang 2024-05-01 12:46:35 -07:00
  • cb1e072643
    Merge pull request #4087 from ollama/mxyng/fix-host-port Michael Yang 2024-05-01 12:42:07 -07:00
  • 45b6a12e45 server: target invalid Michael Yang 2024-05-01 12:39:05 -07:00
  • 68755f1f5e
    chore: fix typo in docs/development.md (#4073) alwqx 2024-05-02 03:39:11 +08:00
  • 997a455039 want filepath Michael Yang 2024-05-01 12:33:41 -07:00
  • 88775e1ff9 strip scheme from name Michael Yang 2024-05-01 12:25:29 -07:00
  • 8867e744ff types/model: fix name for hostport Michael Yang 2024-05-01 12:14:53 -07:00
  • 4fd064bea6
    Merge pull request #4031 from MarkWard0110/fix/issue-3736 Daniel Hiltgen 2024-05-01 12:13:26 -07:00
  • 59fbceedcc
    use lf for line endings (#4085) Jeffrey Morgan 2024-05-01 15:02:45 -04:00
  • 321d57e1a0 Removing go routine calling .wait from load. Mark Ward 2024-05-01 18:49:28 +00:00
  • ba26c7aa00 it will always return an error due to Kill() discarding Wait() errors Mark Ward 2024-04-29 22:48:14 +00:00
  • 63c763685f log when the waiting for the process to stop to help debug when other tasks execute during this wait. expire timer clear the timer reference because it will not be reused. close will clean up expireTimer if calling code has not already done this. Mark Ward 2024-04-29 18:06:56 +00:00
  • 34a4a94f13 ignore debug bin files Mark Ward 2024-04-29 15:05:54 +00:00
  • f4a73d57a4 fix runner expire during active use. Clearing the expire timer as it is used. Allowing the finish to assign an expire timer so that the runner will expire after no use. Mark Ward 2024-04-28 16:43:40 +00:00
  • 948114e3e3 fix sched to wait for the runner to terminate to ensure following vram check will be more accurate Mark Ward 2024-04-28 16:41:38 +00:00
  • 506ff5c26a use lf for line endings jmorganca 2024-05-01 14:41:47 -04:00
  • a3e60d9058
    README.md: fix typos (#4007) Arpit Jain 2024-05-02 02:39:38 +09:00
  • c751af3b21
    Update README.md Blake Mizerany 2024-05-01 10:38:30 -07:00
  • 8acb233668 use strings.Builder Michael Yang 2024-05-01 10:01:09 -07:00
  • 119589fcb3 rename parser to model/file Michael Yang 2024-04-30 10:55:19 -07:00
  • 5ea844964e cmd: import regexp Michael Yang 2024-05-01 09:53:36 -07:00
  • bd8eed57fc fix parser name Michael Yang 2024-04-26 17:11:47 -07:00
  • 9cf0f2e973 use parser.Format instead of templating modelfile Michael Yang 2024-04-26 16:59:31 -07:00
  • 176ad3aa6e parser: add commands format Michael Yang 2024-04-24 18:49:14 -07:00
  • 4d08363580 comments Michael Yang 2024-04-26 15:13:27 -07:00
  • 8907bf51d2 fix multiline Michael Yang 2024-04-24 19:17:26 -07:00
  • abe614c705 tests Michael Yang 2024-04-24 16:12:56 -07:00
  • 238715037d linting Michael Yang 2024-04-24 16:08:51 -07:00
  • c0a00f68ae refactor modelfile parser Michael Yang 2024-04-22 15:37:14 -07:00
  • f0c454ab57
    gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead (#4068) v0.1.33-rc6 Jeffrey Morgan 2024-05-01 11:46:03 -04:00
  • 05eeb01c03
    Small typo Napuh 2024-05-01 17:16:32 +02:00
  • f85e255e8a Added instructions to easily install specific versions on faq.md Napuh 2024-05-01 17:05:41 +02:00
  • 256a946fcb chore: fix typo in docs/development.md alwqx 2024-05-01 17:42:17 +08:00
  • 1c63ed8ef6 gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead jmorganca 2024-04-30 21:55:44 -04:00
  • 089daaeabc Add CUDA Driver API for GPU discovery Daniel Hiltgen 2024-04-30 16:42:48 -07:00
  • 8afe873f17 ... Blake Mizerany 2024-04-30 16:53:47 -07:00
  • 7ba71c3989 ... Blake Mizerany 2024-04-29 21:05:43 -07:00
  • fdef9a0eb2 ... Blake Mizerany 2024-04-29 21:03:06 -07:00
  • b9f74ff3d6
    types/model: reintroduce Digest (#4065) Blake Mizerany 2024-04-30 16:38:03 -07:00
  • a358b71feb
    Merge 2cf8f08aa76c643f0167b25839cba33e54afa0a3 into fcf4d60eeea12b3b25877b09aae2c3e6a38b5bbe Simon Schampijer 2024-04-30 23:03:46 +00:00
  • db0dc60696
    Merge 0662b9b0435220f2ca70f816c4471bd2f8ac7cbe into fcf4d60eeea12b3b25877b09aae2c3e6a38b5bbe Dennis Kruyt 2024-04-30 23:02:20 +00:00
  • 090098b28a types/model: reintroduce Digest Blake Mizerany 2024-04-30 15:52:51 -07:00
  • fcf4d60eee llm: add back check for empty token cache jmorganca 2024-04-30 17:38:44 -04:00
  • e33d5c2dbc update llama.cpp commit to 952d03d jmorganca 2024-04-30 17:31:20 -04:00
  • 18d9a7e1f1
    update llama.cpp submodule to f364eb6 (#4060) Jeffrey Morgan 2024-04-30 17:25:39 -04:00
  • 56ab19dbf5 update llama.cpp submodule to f364eb6 jmorganca 2024-04-30 14:45:43 -04:00
  • 8488388cbd
    Update README.md Michael 2024-04-30 15:45:56 -04:00
  • 45c7f81830 fix: store accurate model parameter size Bruce MacDonald 2024-04-30 11:41:56 -07:00
  • c5708cae1d
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-30 21:35:31 +03:00
  • 588901f449
    types/model: reduce Name.Filepath allocs from 5 to 2 (#4039) Blake Mizerany 2024-04-30 11:09:19 -07:00
  • 0a7fdbe533
    prompt to display and add local ollama keys to account (#3717) Bruce MacDonald 2024-04-30 11:02:08 -07:00
  • d4867f8392 types/model: reduce Name.Filepath allocs from 5 to 2 Blake Mizerany 2024-04-29 22:13:35 -07:00
  • 2f0e092967
    Merge branch 'main' of github.com:alley-team/grammared-ollama Mark CDA 2024-04-30 15:44:22 +03:00
  • 664141d092
    Revert "Merge pull request #2 from alley-team/json-grammar-enhance" Mark CDA 2024-04-30 15:43:36 +03:00
  • 246731cb83
    Merge 7fb8128be5df5c24c122f6ed08de0fc1978bd5ce into 5950c176caf585b04ac517003d1385833e5e4927 Mr. AGI 2024-04-30 14:27:57 +05:00
  • 661ac24b21
    docs: add Guix package manager in README. tusharhero 2024-04-30 13:07:55 +05:30
  • 48e1046064
    Merge branch 'ollama:main' into main Климентий Титов 2024-04-30 10:14:30 +03:00
  • 5950c176ca
    Update langchainpy.md (#4037) Christian Frantzen 2024-04-30 05:19:06 +02:00
  • 23d23409a0
    Update llama.cpp (#4036) Daniel Hiltgen 2024-04-29 20:18:48 -07:00
  • 9f7f6df8dd
    fix(cli): unable to use CLI within the container Kevin Cui 2024-04-30 10:10:53 +08:00
  • 9d6f9a7e5c
    Update langchainpy.md Christian Frantzen 2024-04-30 03:01:36 +02:00
  • 9009bedf13
    better checking for OLLAMA_HOST variable (#3661) Patrick Devine 2024-04-29 19:14:07 -04:00
  • d4ac57e240
    Merge pull request #4035 from dhiltgen/fix_relative_paths Daniel Hiltgen 2024-04-29 16:08:06 -07:00
  • 7b59d1770f Fix relative path lookup Daniel Hiltgen 2024-04-29 16:00:08 -07:00
  • 010b4aaeae still more comments Patrick Devine 2024-04-29 18:50:51 -04:00
  • ef2bb3cb7b more comments Patrick Devine 2024-04-29 18:47:49 -04:00
  • 0aa9cf4c90 Adjust types for bump Daniel Hiltgen 2024-04-29 15:34:37 -07:00
  • 72745e035d Bump llama.cpp to b2761 Daniel Hiltgen 2024-04-29 15:10:04 -07:00
  • 4fecd34bd5 add more tests + omit spaces/quotes Patrick Devine 2024-04-16 13:23:03 -07:00
  • 6883262a72 comments Patrick Devine 2024-04-16 12:39:42 -07:00
  • 89c4f692af better checking for OLLAMA_HOST variable Patrick Devine 2024-04-15 16:33:20 -07:00
  • 4a7c8fdf78 Merge branch 'brucemacd/add-key' of https://github.com/ollama/ollama into brucemacd/add-key Bruce MacDonald 2024-04-29 14:00:09 -07:00
  • 6d0c5acd40 add TODO Bruce MacDonald 2024-04-29 14:00:01 -07:00
  • 41fb983bc4
    Update cmd/cmd.go Bruce MacDonald 2024-04-29 13:16:21 -07:00
  • 827cb3b8b9 Update cmd.go Bruce MacDonald 2024-04-29 10:54:44 -07:00
  • 9aab213160 Update llama.cpp Bruce MacDonald 2024-04-29 10:50:35 -07:00
  • 1fb4008555 PR feedback Bruce MacDonald 2024-04-25 14:10:38 -07:00
  • db572d9cc8 fix build problems Bruce MacDonald 2024-04-24 13:30:42 -07:00
  • 35e54a23a4 check pub key validity before returning Bruce MacDonald 2024-04-24 11:59:57 -07:00
  • 014ebde14f account for ollama.com host Bruce MacDonald 2024-04-22 11:30:00 -07:00
  • 95dda54a72 go mod tidy Bruce MacDonald 2024-04-19 16:33:32 -07:00
  • 8b7dd0c6d2 remove unneeded info log Bruce MacDonald 2024-04-19 16:32:58 -07:00