Commit Graph

  • 53da2c6965
    llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535) v0.2.0 Jeffrey Morgan 2024-07-07 14:32:05 -04:00
  • d8def1ff94
    llm: allow gemma 2 to context shift (#5534) v0.1.49-rc14 Jeffrey Morgan 2024-07-07 13:41:51 -04:00
  • 571dc61955
    Update llama.cpp submodule to a8db2a9c (#5530) Jeffrey Morgan 2024-07-07 13:03:09 -04:00
  • 0e09c380fc
    llm: print caching notices in debug only (#5533) Jeffrey Morgan 2024-07-07 12:38:04 -04:00
  • 0ee87615c7
    sched: don't error if paging to disk on Windows and macOS (#5523) v0.1.49-rc13 Jeffrey Morgan 2024-07-06 22:01:52 -04:00
  • f8241bfba3
    gpu: report system free memory instead of 0 (#5521) v0.1.49-rc12 Jeffrey Morgan 2024-07-06 19:35:04 -04:00
  • 4607c70641
    llm: add -DBUILD_SHARED_LIBS=off to common cpu cmake flags (#5520) Jeffrey Morgan 2024-07-06 18:58:16 -04:00
  • c12f1c5b99 release: move mingw library cleanup to correct job v0.1.49-rc11 jmorganca 2024-07-06 16:12:29 -04:00
  • a08f20d910 release: remove unwanted mingw dll.a files jmorganca 2024-07-06 15:21:15 -04:00
  • 6cea036027 Revert "llm: only statically link libstdc++" jmorganca 2024-07-06 15:10:48 -04:00
  • 5796bfc401 llm: only statically link libstdc++ v0.1.49-rc10 jmorganca 2024-07-06 14:06:20 -04:00
  • f1a379aa56 llm: statically link pthread and stdc++ dependencies in windows build v0.1.49-rc9 jmorganca 2024-07-06 12:54:02 -04:00
  • 9ae146993e llm: add GGML_STATIC flag to windows static lib v0.1.49-rc8 jmorganca 2024-07-06 03:27:05 -04:00
  • 9b58aecd3e llm: build with GGML_STATIC=on for static lib jmorganca/ggml-static jmorganca 2024-07-06 02:50:25 -04:00
  • e0348d3fe8
    llm: add COMMON_DARWIN_DEFS to arm static build (#5513) v0.1.49-rc7 Jeffrey Morgan 2024-07-05 22:42:42 -04:00
  • 2cc854f8cb
    llm: fix missing dylibs by restoring old build behavior on Linux and macOS (#5511) v0.1.49-rc6 Jeffrey Morgan 2024-07-05 21:48:31 -04:00
  • 5304b765b2
    llm: put back old include dir (#5507) Jeffrey Morgan 2024-07-05 19:34:21 -04:00
  • fb6cbc02fb update named templates Michael Yang 2024-06-27 14:15:17 -07:00
  • 4fd5f3526a
    fix cmake build (#5505) v0.1.49-rc5 v0.1.49-rc4 Jeffrey Morgan 2024-07-05 19:07:01 -04:00
  • 842f85f758
    Merge pull request #5502 from dhiltgen/ci_fixes Daniel Hiltgen 2024-07-05 15:39:11 -07:00
  • 9d30f9f8b3 Always go build in CI generate steps Daniel Hiltgen 2024-07-05 12:25:53 -07:00
  • 631cfd9e62
    types/model: remove knowledge of digest (#5500) Blake Mizerany 2024-07-05 13:42:30 -07:00
  • 326363b3a7 no funcs Michael Yang 2024-07-03 13:49:14 -07:00
  • ac7a842e55 fix model reloading Michael Yang 2024-07-03 09:00:07 -07:00
  • 2c3fe1fd97 comments Michael Yang 2024-06-20 11:00:08 -07:00
  • 269ed6e6a2 update message processing Michael Yang 2024-06-17 10:38:55 -07:00
  • 78fb33dd07
    fix typo in cgo directives in llm.go (#5501) Jeffrey Morgan 2024-07-05 15:18:36 -04:00
  • 8f8e736b13
    update llama.cpp submodule to d7fd29f (#5475) Jeffrey Morgan 2024-07-05 13:25:58 -04:00
  • d89454de80
    Use slot with cached prompt instead of least recently used (#5492) Jeffrey Morgan 2024-07-05 12:32:47 -04:00
  • af28b94533
    Merge pull request #5469 from dhiltgen/prevent_system_oom Daniel Hiltgen 2024-07-05 08:22:20 -07:00
  • e9188e971a
    Fix assert on small embedding inputs (#5491) Jeffrey Morgan 2024-07-05 11:20:57 -04:00
  • 78eddfc068
    Merge pull request #4412 from dhiltgen/win_docs Daniel Hiltgen 2024-07-05 08:18:22 -07:00
  • 02c24d3d01
    Merge pull request #5466 from dhiltgen/fix_clip_unicode Daniel Hiltgen 2024-07-05 08:16:58 -07:00
  • 52abc8acb7 Document older win10 terminal problems Daniel Hiltgen 2024-05-13 15:08:29 -07:00
  • 4d71c559b2
    fix error detection by limiting model loading error parsing (#5472) Jeffrey Morgan 2024-07-03 20:04:30 -04:00
  • 0d16eb310e
    fix: use envconfig.ModelsDir directly (#4821) Anatoli Babenia 2024-07-04 01:36:11 +03:00
  • 8072e205ff
    Merge pull request #5447 from dhiltgen/fix_keepalive Daniel Hiltgen 2024-07-03 15:34:38 -07:00
  • 955f2a4e03 Only set default keep_alive on initial model load Daniel Hiltgen 2024-07-02 15:12:43 -07:00
  • 105e36765d token bug corrected Roy Han 2024-07-03 15:03:54 -07:00
  • 3c75113e37 Prevent loading models larger than total memory Daniel Hiltgen 2024-07-03 14:47:42 -07:00
  • 6caac01494 clear comments Roy Han 2024-07-03 14:05:34 -07:00
  • 17de2b4405 Refactoring of legacy and new Roy Han 2024-07-03 14:02:25 -07:00
  • ccd7785859
    Merge pull request #5243 from dhiltgen/modelfile_use_mmap Daniel Hiltgen 2024-07-03 13:59:42 -07:00
  • 3b5a4a77f3
    Return Correct Prompt Eval Count Regardless of Cache Prompt (#5371) royjhan 2024-07-03 13:46:23 -07:00
  • daed0634a9
    Merge pull request #5467 from dhiltgen/bogus_cpu_mac_error Daniel Hiltgen 2024-07-03 13:39:36 -07:00
  • 0d4dd707bc
    Merge pull request #5465 from dhiltgen/better_cuda_logging Daniel Hiltgen 2024-07-03 13:12:22 -07:00
  • 0e982bc1f4 Fix corner cases on tmp cleaner on mac Daniel Hiltgen 2024-07-03 13:10:14 -07:00
  • 922b8f2584 input handling and handler testing Roy Han 2024-07-03 12:48:54 -07:00
  • c0fa2236cf integration float32 Roy Han 2024-07-03 12:47:57 -07:00
  • 6298f49816 Fix clip model loading with unicode paths Daniel Hiltgen 2024-07-03 12:37:40 -07:00
  • a413014aaf refactoring Roy Han 2024-07-03 11:20:55 -07:00
  • a5f23d766e
    Merge branch 'main' into royh-batchembed royjhan 2024-07-03 11:20:24 -07:00
  • ef757da2c9 Better nvidia GPU discovery logging Daniel Hiltgen 2024-07-03 10:30:07 -07:00
  • 95e46eeedf move normalize test Roy Han 2024-07-03 09:45:42 -07:00
  • e5352297d9
    Merge pull request #5448 from ollama/mxyng/fix-generate Michael Yang 2024-07-02 16:48:06 -07:00
  • 65a5040e09 fix generate template Michael Yang 2024-07-02 16:42:17 -07:00
  • d626b99b54
    OpenAI: v1/completions compatibility (#5209) royjhan 2024-07-02 16:01:45 -07:00
  • fa7be5aab4
    Merge branch 'main' into royh-completions-docs royjhan 2024-07-02 14:52:56 -07:00
  • dddb58a38b
    Merge pull request #5051 from ollama/mxyng/capabilities Michael Yang 2024-07-02 14:26:07 -07:00
  • 400056e154
    Merge pull request #5420 from ollama/mxyng/insecure-path Michael Yang 2024-07-02 14:03:23 -07:00
  • d2f19024d0
    Merge pull request #5442 from dhiltgen/concurrency_docs Daniel Hiltgen 2024-07-02 12:47:47 -07:00
  • 69c04eecc4 Add windows radeon concurreny note Daniel Hiltgen 2024-07-02 12:46:14 -07:00
  • 996bb1b85e
    OpenAI: /v1/models and /v1/models/{model} compatibility (#5007) royjhan 2024-07-02 11:50:56 -07:00
  • 422dcc3856
    Merge pull request #5439 from dhiltgen/fix_centos_7_build v0.1.49-rc3 Daniel Hiltgen 2024-07-02 11:01:15 -07:00
  • 3d060e0ae9 move normalize Roy Han 2024-07-02 10:35:02 -07:00
  • 020bd60ab2 Switch amd container image base to rocky 8 Daniel Hiltgen 2024-07-02 10:23:05 -07:00
  • 00a4cb26ca use float32 Roy Han 2024-07-02 10:30:29 -07:00
  • 8e277b72bb
    Merge pull request #5438 from dhiltgen/fix_centos_7_build v0.1.49-rc2 Daniel Hiltgen 2024-07-02 09:28:00 -07:00
  • 4f67b39d26 Centos 7 EOL broke mirrors Daniel Hiltgen 2024-07-02 09:22:17 -07:00
  • 2425281317
    Merge pull request #5336 from ollama/jyan/from-errors v0.1.49-rc1 Josh 2024-07-01 16:32:46 -07:00
  • 0403e9860e
    Merge pull request #5421 from ollama/jyan/ver Josh 2024-07-01 16:32:14 -07:00
  • 512e0a7bde Clean up Roy Han 2024-07-01 16:29:54 -07:00
  • 1a0c8b363c Truncation Integration Tests Roy Han 2024-07-01 16:26:30 -07:00
  • 33a65e3ba3 error Josh Yan 2024-07-01 16:04:13 -07:00
  • 3803ecb6a6 cmd build context mxyng/create-context Michael Yang 2024-06-30 10:24:31 -07:00
  • b662e4706e Remove default auto from help message jyan/v0.146 Daniel Hiltgen 2024-07-01 09:48:05 -07:00
  • be31611ff1 Fix case for NumCtx Daniel Hiltgen 2024-07-01 09:43:59 -07:00
  • 02ba11b614 Document concurrent behavior and settings Daniel Hiltgen 2024-06-28 13:15:57 -07:00
  • 03bb60e036 Sort the ps output Daniel Hiltgen 2024-06-21 15:59:41 -07:00
  • 976fc86978 Disable concurrency for AMD + Windows Daniel Hiltgen 2024-06-19 13:35:38 -07:00
  • 9bceb3b55e Enable concurrency by default Daniel Hiltgen 2024-05-06 17:47:52 -07:00
  • 7add3e5267 Update README.md (#5214) RAPID ARCHITECT 2024-06-30 21:00:57 -05:00
  • c4f2236cf9 Update gpu.md (#5382) Eduard 2024-07-01 03:48:51 +02:00
  • b7ccdcef94 Update api.md Jeffrey Morgan 2024-06-29 16:22:49 -07:00
  • 1f4f46800c Do not shift context for sliding window models (#5368) Jeffrey Morgan 2024-06-28 19:39:31 -07:00
  • 42574d3b11 Include Show Info in Interactive (#5342) royjhan 2024-06-28 13:15:52 -07:00
  • 7bd7e113e3 Ollama Show: Check for Projector Type (#5307) royjhan 2024-06-28 11:30:16 -07:00
  • 20240927f8 Update docs (#5312) royjhan 2024-06-28 09:58:14 -07:00
  • 3af1c58146 gemma2 graph Michael Yang 2024-06-27 10:52:25 -07:00
  • d90b27a57f update readme for gemma 2 (#5333) Michael 2024-06-27 12:45:16 -04:00
  • b7ce14c764 zip: prevent extracting files into parent dirs (#5314) Michael Yang 2024-06-26 21:38:21 -07:00
  • 161229a153 llm: architecture patch (#5316) Jeffrey Morgan 2024-06-26 21:38:12 -07:00
  • bd8d680e26 refactor error Josh Yan 2024-07-01 15:57:57 -07:00
  • a562b9069f refactor error Josh Yan 2024-07-01 15:56:47 -07:00
  • 88bcd79bb9 err on insecure path Michael Yang 2024-06-30 11:10:40 -07:00
  • 5d76e78c2f add error message for unsupported arch Josh Yan 2024-07-01 15:43:03 -07:00
  • e068e7f698 Integration Test Template Roy Han 2024-07-01 15:24:26 -07:00
  • aee25acb5b move normalization to go Roy Han 2024-07-01 14:10:58 -07:00
  • 9c32b6b9ed Truncation Roy Han 2024-07-01 11:59:44 -07:00
  • 1daac52651 Truncation Roy Han 2024-07-01 11:55:16 -07:00