Commit Graph

  • c2d1ce906b restore locale patch Jeffrey Morgan 2024-03-12 21:06:30 -07:00
  • 3e22611200
    token repeat limit for prediction requests (#3080) Bruce MacDonald 2024-03-12 22:08:25 -04:00
  • 7e5e973558 add OLLAMA_KEEP_ALIVE env variable to set the default keep alive Patrick Devine 2024-03-12 19:02:38 -07:00
  • a54d4a28dc
    Merge pull request #3088 from dhiltgen/rocm_igpu_linux Daniel Hiltgen 2024-03-12 17:20:27 -07:00
  • 82b0c7c27e Fix iGPU detection for linux Daniel Hiltgen 2024-03-12 16:57:19 -07:00
  • a989d49e59 Revert "if/else" Bruce MacDonald 2024-03-12 19:49:45 -04:00
  • ba7cf7fb66
    add more docs on for the modelfile message command (#3087) Patrick Devine 2024-03-12 16:41:41 -07:00
  • 3641dfbe1b add more docs on for the modelfile message command Patrick Devine 2024-03-12 16:35:45 -07:00
  • b2fb365508 if/else Bruce MacDonald 2024-03-12 19:14:51 -04:00
  • 2f804068bd
    warn when json format is expected but not mentioned in prompt (#3081) Bruce MacDonald 2024-03-12 19:07:11 -04:00
  • 85129d3a32 Adapt our build for imported server.cpp Daniel Hiltgen 2024-03-12 13:51:44 -07:00
  • 9ac6440da3 Import server.cpp as of b2356 Daniel Hiltgen 2024-03-12 13:49:47 -07:00
  • 0085297928 refactor readseeker Michael Yang 2024-03-09 12:28:36 -08:00
  • 34d00f90b1
    Merge pull request #3070 from dhiltgen/visible_devices Daniel Hiltgen 2024-03-12 11:36:46 -07:00
  • b53229a2ed Add docs explaining GPU selection env vars Daniel Hiltgen 2024-03-11 16:54:38 -07:00
  • 2a4cae6de0 warn when json format is expected but not mentioned in prompt Bruce MacDonald 2024-03-12 14:24:45 -04:00
  • 53c107e20e
    chore: fix typo (#3073) racerole 2024-03-13 02:09:22 +08:00
  • 51578d8573
    fix gpu_info_cuda.c compile warning (#3077) mofanke 2024-03-13 02:08:40 +08:00
  • 480674763c token repeat limit for prediction requests Bruce MacDonald 2024-03-12 14:01:48 -04:00
  • a4725d7199 fix gpu_info_cuda.c compile warning mofanke 2024-03-12 20:40:54 +08:00
  • e9cb6f531b Merge branch 'main' of https://github.com/jesseclin/ollama into main Jesse C. Lin 2024-03-12 20:00:57 +08:00
  • e135e08bd4 Relocate doc position Jesse C. Lin 2024-03-12 19:59:59 +08:00
  • 94a721e1a5 Update Japanese version of documents Jesse C. Lin 2024-03-12 19:58:30 +08:00
  • 55d00e318c chore: fix typo racerole 2024-03-12 16:21:53 +08:00
  • a5d6b5b574
    Merge branch 'ollama:main' into main Jesse C. Lin 2024-03-12 11:02:24 +08:00
  • b5fcd9d3aa
    use -trimpath when building releases (#3069) Jeffrey Morgan 2024-03-11 15:58:46 -07:00
  • 95bcd0ea95 use -trimpath when building releases Jeffrey Morgan 2024-03-11 15:55:18 -07:00
  • b80661e8c7
    relay load model errors to the client (#3065) Bruce MacDonald 2024-03-11 16:48:27 -04:00
  • 6d3adfbea2
    Update troubleshooting.md Jeffrey Morgan 2024-03-11 13:22:28 -07:00
  • df3ad304c8 relay load model errors to the client Bruce MacDonald 2024-03-11 16:19:46 -04:00
  • 369eda65f5
    update llama.cpp submodule to ceca1ae (#3064) Jeffrey Morgan 2024-03-11 12:57:48 -07:00
  • e7a5abdbf4
    Merge branch 'main' into override_default_threads lainedfles 2024-03-11 19:33:41 +00:00
  • b4671864b2 update llama.cpp submodule to ceca1ae Jeffrey Morgan 2024-03-11 11:56:36 -07:00
  • f878e91070
    Merge pull request #3044 from ollama/mxyng/fix-convert-shape Michael Yang 2024-03-11 09:56:57 -07:00
  • 5e109f2085 Add ROCm support to linux install script Daniel Hiltgen 2024-03-06 17:08:29 -08:00
  • 0d651478e4
    Merge pull request #3056 from dhiltgen/rocm_link_clash Daniel Hiltgen 2024-03-11 09:48:48 -07:00
  • 9ea492f1ce convert: fix shape Michael Yang 2024-03-10 10:41:40 -07:00
  • bc13da2bfe Avoid rocm runner and dependency clash Daniel Hiltgen 2024-03-11 08:45:57 -07:00
  • 97d488bfa0
    Merge branch 'main' into main fly2tomato 2024-03-11 14:05:36 +08:00
  • 41b00b9856 fix 03-locale.diff Jeffrey Morgan 2024-03-10 16:21:05 -07:00
  • c2a8ed48e7
    Merge pull request #3048 from dhiltgen/harden_rocm_deps Daniel Hiltgen 2024-03-10 15:17:22 -07:00
  • d10d3aac58 disable execstack for amd libraries jmorganca/execstack Jeffrey Morgan 2024-03-10 15:02:19 -07:00
  • 3dc1bb6a35 Harden for deps file being empty (or short) Daniel Hiltgen 2024-03-10 14:45:38 -07:00
  • 7865a6996a
    Merge pull request #3046 from dhiltgen/rocm_search_paths Daniel Hiltgen 2024-03-10 12:30:56 -07:00
  • 00ec269321 Add ollama executable peer dir for rocm Daniel Hiltgen 2024-03-10 12:13:46 -07:00
  • 239e8b7527
    Fix paste of text with line feed characters Giuseppe Lumia 2024-03-10 16:42:38 +01:00
  • 908005d90b
    patch: use default locale in wpm tokenizer (#3034) Jeffrey Morgan 2024-03-09 21:12:12 -08:00
  • 6e1cf27678 patch: use default locale in wpm tokenizer Jeffrey Morgan 2024-03-09 20:49:20 -08:00
  • 0779699271
    docs: Add AI telegram to Community Integrations. tusharhero 2024-03-10 09:32:25 +05:30
  • cdf65e793f only copy deps for amd64 in build_linux.sh Jeffrey Morgan 2024-03-09 17:55:22 -08:00
  • 82ca694d68
    Rename ROCm deps file to avoid confusion (#3025) Daniel Hiltgen 2024-03-09 17:48:38 -08:00
  • 5017a15bcb add macapp to .dockerignore Jeffrey Morgan 2024-03-09 16:07:06 -08:00
  • e11668aa07 add bundle_metal and cleanup_metal funtions to gen_darwin.sh Jeffrey Morgan 2024-03-09 16:04:57 -08:00
  • 0bd0f4a29c tidy cleanup logs Jeffrey Morgan 2024-03-09 15:56:48 -08:00
  • 1ffb1e2874
    update llama.cpp submodule to 77d1ac7 (#3030) Jeffrey Morgan 2024-03-09 15:55:34 -08:00
  • aa0844bc1e update llama.cpp submodule to 77d1ac7 Jeffrey Morgan 2024-03-09 14:08:34 -08:00
  • 0a7844413c
    Merge pull request #3026 from dhiltgen/win_rocm_docs Daniel Hiltgen 2024-03-09 14:17:19 -08:00
  • 5cddfc14c9 Refine nvidia discovery for windows build script Daniel Hiltgen 2024-03-07 17:00:17 -08:00
  • 111b764c6e Fix ARM container build Daniel Hiltgen 2024-03-07 15:50:06 -08:00
  • 8ec691837a Logging improvement for memory reporting Daniel Hiltgen 2024-03-07 11:23:31 -08:00
  • 98e7174101 Wire up more complete CI for releases Daniel Hiltgen 2024-03-07 10:54:21 -08:00
  • f9cd55c70b disable gpu for certain model architectures and fix divide-by-zero on memory estimation Jeffrey Morgan 2024-03-09 12:51:38 -08:00
  • 0fdebb34a9 Doc how to set up ROCm builds on windows Daniel Hiltgen 2024-03-09 11:29:45 -08:00
  • 5358e09c8e Rename ROCm deps file to avoid confusion Daniel Hiltgen 2024-03-09 11:20:07 -08:00
  • a3d809c21e
    Snap packaging Matias Piipari 2024-03-09 21:10:18 +02:00
  • cd493e8b65
    Merge branch 'main' into add-webui-link-to-readme-alpaca Miguel 2024-03-09 18:33:09 +01:00
  • ac64cd4ef9
    Merge pull request #3008 from dhiltgen/no_more_idempotent Daniel Hiltgen 2024-03-09 09:13:24 -08:00
  • 4a5c9b8035 Finish unwinding idempotent payload logic Daniel Hiltgen 2024-03-08 09:45:55 -08:00
  • efe5617b64
    update llama.cpp submodule to c2101a2 (#3020) Jeffrey Morgan 2024-03-09 00:44:50 -08:00
  • 8eca59fa7a update llama.cpp submodule to c2101a2 Jeffrey Morgan 2024-03-09 00:24:04 -08:00
  • 5b3fad9636 separate out isLocalIP Jeffrey Morgan 2024-03-09 00:22:08 -08:00
  • bfec2c6e10 simplify host checks Jeffrey Morgan 2024-03-08 23:29:53 -08:00
  • 5c143af726 add additional allowed hosts Jeffrey Morgan 2024-03-08 23:23:59 -08:00
  • 9cae8446a1 Revert debug log Self Denial 2024-03-08 23:56:04 -07:00
  • 6c0af2599e
    Update docs README.md and table of contents Jeffrey Morgan 2024-03-08 22:45:11 -08:00
  • fc8c044584
    add allowed host middleware and remove workDir middleware (#3018) Jeffrey Morgan 2024-03-08 22:23:47 -08:00
  • 46e9d065fe add host middleware and remove workDir middleware Jeffrey Morgan 2024-03-08 22:12:49 -08:00
  • 7494a0e86c
    Merge f94847190df0dd275c34dab1543fe6487fd56b0c into ecc133d843c8567b27ff3bdc9ff811ecad99281a da-z 2024-03-09 06:19:30 +05:30
  • ecc133d843
    Merge pull request #3014 from ollama/mxyng/decode-ggla Michael Yang 2024-03-08 16:14:53 -08:00
  • 76bdebbadf decode ggla Michael Yang 2024-03-08 15:38:53 -08:00
  • 18979ad4a1 convert: fix default shape Michael Yang 2024-03-08 15:40:16 -08:00
  • 8e0ef931d8
    Merge pull request #2990 from ollama/mxyng/default-term-size Michael Yang 2024-03-08 15:20:54 -08:00
  • 280da44522
    Merge pull request #2988 from dhiltgen/rocm_docs Daniel Hiltgen 2024-03-08 13:33:30 -08:00
  • 0cebc79cba
    fix: allow importing a model from name reference (#3005) Bruce MacDonald 2024-03-08 12:27:47 -05:00
  • b5d164076d fix: allow importing a model from name reference Bruce MacDonald 2024-03-08 12:05:39 -05:00
  • 6023044af3 replace assets on load jmorganca/replace-assets Jeffrey Morgan 2024-03-08 00:44:22 -08:00
  • 0e4669b04f
    update llama.cpp submodule to 6cdabe6 (#2999) Jeffrey Morgan 2024-03-08 00:26:20 -08:00
  • 957ac3af2f update llama.cpp submodule to 6cdabe6 Jeffrey Morgan 2024-03-07 21:47:39 -08:00
  • b886bec3f9
    Update api.md Jeffrey Morgan 2024-03-07 23:27:51 -08:00
  • bca3705f2d chore(buffer): use errors.Join to combine all possible errors when trying to get term size from stdout, stderr, and /dev/tty yuyi 2024-03-08 13:14:32 +08:00
  • eb7a7ecdfe fix(buffer): set default term size if getTermSize() fails yuyi 2024-03-08 10:28:56 +08:00
  • 15efa1c562 fix(buf): #2970 get term size from stderr and /dev/tty Wangshuyi 2024-03-07 23:38:42 +08:00
  • fc06205971
    Revert "adjust download and upload concurrency based on available bandwidth" (#2995) Jeffrey Morgan 2024-03-07 18:10:16 -08:00
  • f90d083d5f
    Revert "adjust download and upload concurrency based on available bandwidth" Jeffrey Morgan 2024-03-07 18:09:12 -08:00
  • 39374984ef set limit to increment mxyng/tune-concurrency Michael Yang 2024-03-07 17:31:45 -08:00
  • ff806c505e
    Merge branch 'ollama:main' into patch-api Christian Neff 2024-03-08 02:19:15 +01:00
  • daf928fe1a tune concurrency manager Michael Yang 2024-03-07 14:18:25 -08:00
  • 2ada81e068
    cmd: tighten up env var usage sections (#2962) Blake Mizerany 2024-03-07 13:57:07 -08:00
  • f1a7def792 cmd: tighten up env var usage sections Blake Mizerany 2024-03-07 13:21:04 -08:00
  • b1e74d4fda default terminal width, height Michael Yang 2024-03-07 11:28:41 -08:00