Commit Graph

  • d412ca4a1e test-release root 2024-10-22 08:23:39 +00:00
  • 958e145246
    Merge 3c40a142475e5d9ab9c9c9ced5cc625727965d81 into 23f746508d1685bc1bbee9ac4cd600bf5f8e6167 COPILOT-WEB-ui 2024-10-22 10:14:07 +02:00
  • d0560fc282
    Delete duplication code Reset() zhanluxianshen 2024-10-22 15:29:35 +08:00
  • d9a2154d51 test-release root 2024-10-22 06:48:11 +00:00
  • e693ec4ea4 test-release root 2024-10-22 06:36:29 +00:00
  • 05de33f852
    Merge branch 'main' into patch-1 Philippe Charrière 2024-10-22 08:26:32 +02:00
  • 23f746508d
    readme: add Ollama for Swift to the community integrations (#7295) Mattt 2024-10-21 22:29:11 -07:00
  • 0348aab83d test-release root 2024-10-22 05:05:07 +00:00
  • def21a7e52 Fix rocm windows build and clean up dependency gathering Daniel Hiltgen 2024-10-21 11:09:44 -07:00
  • 3c40a14247
    Update README.md COPILOT-WEB-ui 2024-10-21 16:48:41 -04:00
  • 10802044b8
    Merge branch 'main' into pull_model_without_serving Adrian Hesketh 2024-10-21 14:57:26 +01:00
  • 9192e4630c
    Add Ollama for Swift to the community integrations Mattt Zmuda 2024-10-21 06:30:56 -07:00
  • 8aa9b6b4d2
    Update release.yaml kavita-rane2 2024-10-21 17:30:16 +05:30
  • baace12177
    Update latest.yaml kavita-rane2 2024-10-21 17:03:45 +05:30
  • 3eb2e5d10d
    Update latest.yaml kavita-rane2 2024-10-21 16:59:58 +05:30
  • ab4372f414
    Update release.yaml kavita-rane2 2024-10-21 16:56:52 +05:30
  • 2a30c9acbd test-latest root 2024-10-21 08:20:49 +00:00
  • e8e1fb63df
    Update release.yaml kavita-rane2 2024-10-21 13:38:31 +05:30
  • 04c388cddb Version Alessandro de Oliveira Faria (A.K.A. CABELO) 2024-10-20 22:48:42 -03:00
  • d218e6ce29
    Reuse type InvalidModelNameErrMsg, unify the const parameters. zhanluxianshen 2024-10-21 06:36:41 +08:00
  • 22146e953e added formatting to ollama ls Roberto Tomás Collins 2024-10-20 18:38:33 -04:00
  • 3534c0d46a
    Merge branch 'main' into feature/kv-quant Sam 2024-10-21 07:24:49 +11:00
  • e647b7e8e2 revert changes to .gitignore José Carlos García 2024-10-20 08:54:11 +02:00
  • f0a97fca42 Implemented split-mode row and nkvo Alex Heisler 2024-10-19 21:12:29 -04:00
  • 34d27d17af
    Update index.ts Hichem Fantar 2024-10-20 00:08:41 +01:00
  • 48708ca0d5
    server: allow vscode-webview origin (#7273) Jeffrey Morgan 2024-10-19 17:06:41 -04:00
  • 80c2f2e734 tests jmorganca 2024-10-19 13:03:25 -07:00
  • 70665e2f08 server: allow vscode-webview origins jmorganca 2024-10-19 12:53:19 -07:00
  • f3f5f38e67 Move win dep gathering to build_windows.ps1 v0.4.0-rc3 Daniel Hiltgen 2024-10-18 20:06:00 -07:00
  • b30e97091f Move win dep gathering to build_windows.ps1 v0.4.0-rc2 Daniel Hiltgen 2024-10-18 20:06:00 -07:00
  • 62ec522268 Refactor context shift flag for infinite text generation comment (should be "infinite") not inifinite Yassineosip 2024-10-19 15:21:32 +01:00
  • dad6cdfaba Move win dep gathering to build_windows.ps1 v0.4.0-rc1 Daniel Hiltgen 2024-10-18 20:06:00 -07:00
  • 4ef972bab0
    migrate from centos7 & gcc10.2 to rocky8 * gcc11.2 Drew Paettie 2024-10-18 18:18:11 -07:00
  • 0a9aff3ebd feat: allow setting KV cache type Sam 2024-10-19 12:52:16 +11:00
  • b5d1677a4e Remove llama.cpp submodule and shift new build to top v0.4.0-rc0 Daniel Hiltgen 2024-10-09 13:52:36 -07:00
  • 4bbdbbcaef Move Go code out of llm package Daniel Hiltgen 2024-10-08 13:54:25 -07:00
  • 0d2cd6345c Remove llama.cpp submodule and shift new build to top v0.4.0-ci3 Daniel Hiltgen 2024-10-09 13:52:36 -07:00
  • c7cb0f0602
    image processing for llama3.2 (#6963) Patrick Devine 2024-10-18 16:12:35 -07:00
  • 90dc81e064 Expose stop sequence Owen Law 2024-10-18 18:57:04 -04:00
  • 5b135a60a5 Fix truncation of end of text when streaming with stop strings Owen Law 2024-10-18 17:52:29 -04:00
  • 5e699c3e4a Add CLI for info command Daniel Hiltgen 2024-10-15 14:28:41 -07:00
  • 78428a8ba0 Wire up API for info UX Daniel Hiltgen 2024-10-13 17:21:38 -07:00
  • 5d988a6d7a
    Update README.md TheCookingSenpai 2024-10-18 21:58:01 +02:00
  • 4aa787a8ca Adding Yacana agents framework to the list of community integrations Doctor 2024-10-18 19:46:25 +02:00
  • 86c11fea46
    Update README.md COPILOT-WEB-ui 2024-10-18 13:38:53 -04:00
  • 8fa0d3773f
    Merge 65813010d8bbaa9189d38efc71198c0c9d25561f into bf4018b9ecd56a5deff0c22ca2fba242a8f0101b Daniel Hiltgen 2024-10-18 22:50:45 +09:00
  • df4d3ec493 test-runner root 2024-10-18 05:53:46 +00:00
  • f14a3c33e9 test-runner root 2024-10-18 05:42:53 +00:00
  • 7d738a35c0 test-runner root 2024-10-18 05:31:37 +00:00
  • 26806174be test-runner root 2024-10-18 05:08:37 +00:00
  • 26b560869e default to "FROM ." if a Modelfile isn't present Patrick Devine 2024-10-16 11:51:07 -07:00
  • 82f349f1c7 fix #7247 - invalid image input Bill Wang 2024-10-18 14:31:30 +11:00
  • ae05598df2 fix #7247 - invalid image input Bill Wang 2024-10-18 14:27:21 +11:00
  • ea11cb4ff4 image processing for llama3.2 Patrick Devine 2024-09-25 11:54:43 -07:00
  • 990aa03dc5
    Merge c9c0e24a87e5821e1ca7234a4bfa79244a13fe84 into bf4018b9ecd56a5deff0c22ca2fba242a8f0101b Amila Kumaranayaka 2024-10-17 23:57:42 +01:00
  • 1c7ad0a791 Move Go code out of llm package Daniel Hiltgen 2024-10-08 13:54:25 -07:00
  • bf4018b9ec
    llama: Decouple patching script from submodule (#7139) Daniel Hiltgen 2024-10-17 15:03:09 -07:00
  • 6b74155896 Run new make sync and patch flow Daniel Hiltgen 2024-10-10 16:28:18 -07:00
  • 86b43f6f95 Refine llama.cpp vendoring workflow tools Daniel Hiltgen 2024-10-09 17:37:15 -07:00
  • f86d00cd95
    llama: add compiler tags for cpu features (#7137) Daniel Hiltgen 2024-10-17 13:43:20 -07:00
  • dcafde2656 llama: add compiler tags for cpu features Daniel Hiltgen 2024-09-27 12:16:36 -07:00
  • f2890a4494
    IBM granite/granitemoe architecture support (#6760) v0.3.14-rc0 v0.3.14 Gabe Goodhart 2024-10-17 12:59:52 -06:00
  • e3e27c266e fix(llm): Remove use of deprecated --log-disable flag Gabe Goodhart 2024-10-17 12:21:27 -06:00
  • 3edf4159ab fix(llama): Remove unnecessary patch for gguf impl header Gabe Goodhart 2024-10-17 12:17:38 -06:00
  • d432f10703 fix(llama/sampling): Use gpt_sampler with a forward declaration Gabe Goodhart 2024-10-17 12:11:49 -06:00
  • 7d371faab2 test-runner root 2024-10-17 14:00:12 +00:00
  • f24b68b348 test-runner root 2024-10-17 13:21:24 +00:00
  • 5e474b5afd test-runner root 2024-10-17 13:14:04 +00:00
  • c4223b68d9 test-runner root 2024-10-17 13:01:38 +00:00
  • 11bd0d9a9f test-runner root 2024-10-17 12:49:34 +00:00
  • 0658cc01ff test-runner root 2024-10-17 12:42:42 +00:00
  • 0a70924bc2 test-runner root 2024-10-17 12:36:22 +00:00
  • 12f2bc3afc test-runner root 2024-10-17 12:28:23 +00:00
  • afe121f197 test-runner root 2024-10-17 12:15:20 +00:00
  • a61ee6e756 runner: Flush pending responses before returning Jesse Gross 2024-09-11 14:00:20 -07:00
  • 74a4bb4032 test-runner root 2024-10-17 11:54:09 +00:00
  • c3ec1f64ec
    Merge branch 'main' into add-web-tool-integration 毛巳煜 2024-10-17 14:22:29 +08:00
  • 3d44c0a45e fix(llama): Fix patch 05 to use new wrapper api and re-sync Gabe Goodhart 2024-10-16 22:02:16 -06:00
  • ea104bd81e fix(llama): Better naming for sampling wrapper and args Gabe Goodhart 2024-10-16 21:59:56 -06:00
  • a85207ff65 fix(llama): Remove TODO about grammar_first Gabe Goodhart 2024-10-16 13:01:12 -06:00
  • 6d68dde8bf fix(llm): Fix missing <thread> include in ext_server Gabe Goodhart 2024-10-16 12:44:02 -06:00
  • 1c6bdf9975 chore(gofumpt): Format on llama.go to pass linting Gabe Goodhart 2024-10-16 12:41:35 -06:00
  • 6bedbcd33a fix(sync): Remove bash-specific change to sync.sh Gabe Goodhart 2024-10-16 07:05:29 -06:00
  • 34fbcde1dd fix(llama): Remove unused SampleTokenGreedy Gabe Goodhart 2024-10-16 06:50:00 -06:00
  • c030e259d0 fix(llama): Fix the impl of SampleTokenGreedy for new sampling Gabe Goodhart 2024-10-14 16:33:28 -06:00
  • 1807e3e51c fix(llama): Overhaul use of sampling module for llama.cpp changes Gabe Goodhart 2024-10-14 16:12:39 -06:00
  • 6d3eac09e6 fix(llama): Add missing log.cpp Gabe Goodhart 2024-10-14 14:43:03 -06:00
  • cef125a162 fix(llama/sync): Add missing ggml-cpu-impl.h copy-over in sync.sh Gabe Goodhart 2024-10-14 13:21:50 -06:00
  • d128c7d82d fix(llama/patches): Add a patch and update for missing ggml-impl.h include Gabe Goodhart 2024-10-14 13:21:10 -06:00
  • cd9337faab feat(llama)!: Rough sync with llama.cpp submodule Gabe Goodhart 2024-10-14 10:30:38 -06:00
  • 697af37a88 fix(llama/patches): Update llama patches Gabe Goodhart 2024-10-14 08:46:58 -06:00
  • 7bae52d933 feat(llama): Always run sync.sh from the right directory Gabe Goodhart 2024-10-14 07:10:01 -06:00
  • 519176f113 fix(patches): Update all patches for latest bump Gabe Goodhart 2024-10-01 14:17:03 -06:00
  • 97a627324e feat(llama.cpp): Bump to the latest master of llama.cpp Gabe Goodhart 2024-10-01 13:40:24 -06:00
  • 44d25a1dbf fix(solar): Update the solar-pro patch for latest llama.cpp bump Gabe Goodhart 2024-09-25 07:29:10 -06:00
  • ce4c665290 feat(llama.cpp): Bump llama.cpp for granitemoe support Gabe Goodhart 2024-09-25 07:28:47 -06:00
  • 35ed3f9201 feat(llama.cpp): Bump llama.cpp for granitemoe support Gabe Goodhart 2024-09-25 06:42:58 -06:00
  • 1063e6e967 fix(solar): Update solar patch for llama.cpp bump Gabe Goodhart 2024-09-19 20:21:16 -06:00
  • 66a4081036 fix(patches): Update all patches (except solar-pro) to work with bumped llama.cpp Gabe Goodhart 2024-09-19 17:12:05 -06:00
  • 61c9667381 feat: Bump llama.cpp to the latest master with granite support Gabe Goodhart 2024-09-19 16:24:23 -06:00