Commit Graph

  • 24636dfa87
    Discovery CPU details for default thread selection (#6264) main Daniel Hiltgen 2024-10-15 11:36:08 -07:00
  • 1d7fa3ad2d
    Adding 'Ollama App' as community integrations (#6465) JHubi1 2024-10-15 18:57:32 +02:00
  • 09035b71cd
    Add missing BF16 tensor type. (#7193) frob 2024-10-15 02:06:35 +02:00
  • f3c8b898cd
    Track GPU discovery failure information (#5820) Daniel Hiltgen 2024-10-14 16:26:45 -07:00
  • 5dd0477fd4
    Fix regression on older macos versions (#7192) Daniel Hiltgen 2024-10-13 10:47:42 -07:00
  • c3d321d405
    llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174) Daniel Hiltgen 2024-10-12 09:56:49 -07:00
  • ce6fee43ee fix cuda unpad kernel pdevine/imageproc Michael Yang 2024-10-11 17:01:22 -07:00
  • a795cbc934 sync and fix warning Michael Yang 2024-10-11 16:56:50 -07:00
  • 12b9cac2ee fix for metal Michael Yang 2024-10-10 12:05:27 -07:00
  • fe6cd26fc7 fix unit tests Jesse Gross 2024-10-10 14:27:45 -07:00
  • ce58885181 image processing for llama3.2 Patrick Devine 2024-09-25 11:54:43 -07:00
  • db95c3c7c3 trim trailing space after image extraction mxyng/mllama Michael Yang 2024-10-09 17:00:23 -07:00
  • 7fe3902552 cli: Send all images in conversation history v0.3.13 Jesse Gross 2024-10-09 20:46:27 -07:00
  • e88ca714f0 more integration Michael Yang 2024-09-30 11:34:30 -07:00
  • 75a07dd8f7 integrate mllama.cpp to server.cpp Michael Yang 2024-09-30 11:13:49 -07:00
  • cb1118c842 draft: mllama vision encoder Michael Yang 2024-09-25 18:12:28 -07:00
  • 0077e22d52 runner.go: Handle truncation of tokens for stop sequences Jesse Gross 2024-10-09 16:12:23 -07:00
  • 03408f3437 server: Don't clear cmd when closing a server Jesse Gross 2024-10-09 16:55:34 -07:00
  • cd7e01e8b9
    fix vendoring attribute for metal (#7156) Daniel Hiltgen 2024-10-09 15:22:36 -07:00
  • af613bab33 fix prompting Patrick Devine 2024-10-09 14:24:36 -07:00
  • 7a962bd802
    fix vendoring attribute (#7155) Daniel Hiltgen 2024-10-09 14:21:02 -07:00
  • b54dcc750c update .gitattributes with proper linguist-vendored entry jmorganca/ga jmorganca 2024-10-09 13:52:33 -07:00
  • 6cb0abf6d8 add compositing for pngs Patrick Devine 2024-10-08 18:46:58 -07:00
  • 3a1c8da5e4 only allow a single image to be passed Patrick Devine 2024-10-08 18:30:07 -07:00
  • f9584deba5
    Fix build leakages (#7141) Daniel Hiltgen 2024-10-08 13:04:59 -07:00
  • 96efd9052f
    Re-introduce the llama package (#5034) Jeffrey Morgan 2024-10-08 11:53:54 -04:00
  • de982616f1
    readme: replace stale links to LangChain documentation (#7117) Shifra Goldstone 2024-10-07 21:16:56 -04:00
  • 03cf7627ec change resize algorithm Patrick Devine 2024-10-06 17:15:44 -07:00
  • defbf9425a
    readme: add G1 to list of community integrations (#7096) hidden1nin 2024-10-05 14:57:53 -04:00
  • f40bb398f6
    Stop model before deletion if loaded (fixed #6957) (#7050) Alex Mavrogiannis 2024-10-01 15:45:43 -07:00
  • 71e76f8c90 server.cpp: cleanup cross attention state jmorganca 2024-09-26 23:53:12 -07:00
  • 7d5e0ff80e add server.cpp and patches jmorganca 2024-09-26 23:04:06 -07:00
  • 79d3b1e2bd
    readme: add ARGO LLM tool to community integrations (#7027) zmldndx 2024-09-30 04:01:01 +08:00
  • 5486c57364 fix template / imageproc issues Patrick Devine 2024-09-26 22:39:45 -07:00
  • 03608cb46e
    server: close response body on error (#6986) Blake Mizerany 2024-09-26 12:00:31 -07:00
  • a2d33ee390 linter feeding Patrick Devine 2024-09-26 02:15:17 -07:00
  • 96a8b2f7d8 fix prompt for non-mllama multimodal Patrick Devine 2024-09-26 01:31:53 -07:00
  • c48e2cfc0d more fixes for mllama Patrick Devine 2024-09-26 01:16:41 -07:00
  • 22d861dfe2 update patch jmorganca/mllama jmorganca 2024-09-25 22:09:38 -07:00
  • 055cb6b0e2 update server.cpp changes jmorganca 2024-09-25 21:54:23 -07:00
  • d0c8ce5ea4 llm: add server entrypoint for mllama jmorganca 2024-09-25 14:37:28 -07:00
  • 8ac915f709 llm: add mllama language support jmorganca 2024-09-25 13:49:10 -07:00
  • 5da1043680 feed the linter Patrick Devine 2024-09-25 13:08:08 -07:00
  • f8ed545cbb image processing for llama3.2 Patrick Devine 2024-09-25 11:54:43 -07:00
  • 450acb71a6
    readme: fix llama3.1 -> llama3.2 typo (#6962) Xe Iaso 2024-09-25 11:53:47 -07:00
  • 55ea963c9e
    update default model to llama3.2 (#6959) Jeffrey Morgan 2024-09-25 11:11:22 -07:00
  • e9e9bdb8d9
    CI: Fix win arm version defect (#6940) v0.3.12 Daniel Hiltgen 2024-09-24 15:18:10 -07:00
  • 35bb6d32b3
    readme: update llamaindex links (#6939) Alex Yang 2024-09-24 12:15:43 -07:00
  • 98701b58b3
    readme: add LLMChat to community integrations (#6919) Deep Lakhani 2024-09-23 20:49:46 -04:00
  • ad935f45ac
    examples: use punkt_tab instead of punkt (#6907) v0.3.12-rc5 Mahesh Sathiamoorthy 2024-09-22 07:25:28 +05:30
  • dbba73469d
    runner: Set windows above normal priority (#6905) Daniel Hiltgen 2024-09-21 16:54:49 -07:00
  • 6c2eb73a70
    Fix missing dep path on windows CPU runners (#6884) Daniel Hiltgen 2024-09-21 16:28:29 -07:00
  • 2a038c1d7e
    CI: win arm artifact dist dir (#6900) v0.3.12-rc4 Daniel Hiltgen 2024-09-20 19:16:18 -07:00
  • 616c5eafee
    CI: win arm adjustments (#6898) v0.3.12-rc3 Daniel Hiltgen 2024-09-20 16:58:56 -07:00
  • f5ff917b1d
    CI: adjust step ordering for win arm to match x64 (#6895) v0.3.12-rc2 Daniel Hiltgen 2024-09-20 14:20:57 -07:00
  • d632e23fba
    Add Windows arm64 support to official builds (#5712) v0.3.12-rc1 Daniel Hiltgen 2024-09-20 13:09:38 -07:00
  • 5804cf1723
    documentation for stopping a model (#6766) Patrick Devine 2024-09-18 16:26:42 -07:00
  • bf7ee0f4d4
    examples: add python examples for bespoke-minicheck (#6841) Ryan Marten 2024-09-18 09:35:25 -07:00
  • b8af12ceaf feed the linter pdevine/newlines Patrick Devine 2024-09-17 18:19:31 -07:00
  • 6f041ddfa4 allow ctl-j to add a new line + fix multiline bracketed paste Patrick Devine 2024-09-17 18:12:55 -07:00
  • 504a410f02
    llm: add solar pro (preview) (#6846) v0.3.11 Michael Yang 2024-09-17 18:11:26 -07:00
  • d05da29912
    server: add tool parsing support for nemotron-mini (#6849) Jeffrey Morgan 2024-09-17 18:06:16 -07:00
  • 72962c6e08
    Merge pull request #6833 from ollama/mxyng/git-am Michael Yang 2024-09-17 16:33:23 -07:00
  • 7bd7b02712 make patches git am-able Michael Yang 2024-09-16 15:58:55 -07:00
  • 8f9ab5e14d
    CI: dist directories no longer present (#6834) v0.3.11-rc4 Daniel Hiltgen 2024-09-16 17:31:37 -07:00
  • 7717bb6a84
    CI: clean up naming, fix tagging latest (#6832) v0.3.11-rc3 Daniel Hiltgen 2024-09-16 16:18:41 -07:00
  • 0ec2915ea7
    CI: set platform build build_linux script to keep buildx happy (#6829) v0.3.11-rc2 Daniel Hiltgen 2024-09-16 14:07:29 -07:00
  • c9a7541b9c
    readme: add Agents-Flex to community integrations (#6788) v0.3.11-rc1 Michael Yang 2024-09-17 04:42:52 +08:00
  • d81cfd7d6f
    fix typo in import docs (#6828) Patrick Devine 2024-09-16 11:48:14 -07:00
  • b330c830d3
    readme: add vim-intelligence-bridge to Terminal section (#6818) Pepo 2024-09-15 20:20:36 -05:00
  • d889c6fd07
    readme: add Obsidian Quiz Generator plugin to community integrations (#6789) Edward Cui 2024-09-14 20:52:37 -07:00
  • 56b9af336a
    Fix incremental builds on linux (#6780) Daniel Hiltgen 2024-09-13 08:24:08 -07:00
  • 7359c5ea5e usage templating mxyng/environ-2 Michael Yang 2024-07-05 15:26:42 -07:00
  • fda0d3be52
    Use GOARCH for build dirs (#6779) Daniel Hiltgen 2024-09-12 16:38:05 -07:00
  • cd5c8f6471
    Optimize container images for startup (#6547) Daniel Hiltgen 2024-09-12 12:10:30 -07:00
  • fef257c5c5
    examples: updated requirements.txt for privategpt example dcasota 2024-09-12 03:56:56 +02:00
  • d066d9b8e0
    examples: polish loganalyzer example (#6744) Adrian Cole 2024-09-12 09:37:37 +08:00
  • 5a00dc9fc9
    readme: add ollama_moe to community integrations (#6752) RAPID ARCHITECT 2024-09-11 20:36:26 -05:00
  • c354e87809
    Merge pull request #6767 from ollama/jessegross/bug_6707 Jesse Gross 2024-09-11 17:20:22 -07:00
  • 93ac3760cb runner: Flush pending responses before returning Jesse Gross 2024-09-11 14:00:20 -07:00
  • abed273de3
    add "stop" command (#6739) Patrick Devine 2024-09-11 16:36:21 -07:00
  • 034392624c
    Merge pull request #6762 from ollama/mxyng/show-output Michael Yang 2024-09-11 14:58:40 -07:00
  • ecab6f1cc5 refactor show ouput Michael Yang 2024-09-11 11:01:30 -07:00
  • 7d6900827d
    readme: add QodeAssist to community integrations (#6754) Petr Mironychev 2024-09-11 22:19:49 +02:00
  • 9246e6dd15
    Verify permissions for AMD GPU (#6736) Daniel Hiltgen 2024-09-11 11:38:25 -07:00
  • 735a0ca2e4
    Merge pull request #6732 from ollama/mxyng/debug-proxy Michael Yang 2024-09-10 16:13:25 -07:00
  • dddb72e084 add *_proxy for debugging Michael Yang 2024-09-10 09:36:42 -07:00
  • 83a9b5271a
    docs: update examples to use llama3.1 (#6718) Jeffrey Morgan 2024-09-09 22:47:16 -07:00
  • 4a8069f9c4
    Quiet down dockers new lint warnings (#6716) Daniel Hiltgen 2024-09-09 17:22:20 -07:00
  • 84b84ce2db
    catch when model vocab size is set correctly (#6714) Patrick Devine 2024-09-09 17:18:54 -07:00
  • bb6a086d63
    readme: add crewAI to community integrations (#6699) Jeffrey Morgan 2024-09-08 00:36:24 -07:00
  • 30c8f201cc
    readme: add crewAI with mesop to community integrations RAPID ARCHITECT 2024-09-08 02:35:59 -05:00
  • 06d4fba851
    openai: align chat temperature and frequency_penalty options with completion (#6688) v0.3.10 frob 2024-09-07 18:08:08 +02:00
  • 108fb6c1d1
    docs: improve linux install documentation (#6683) Jeffrey Morgan 2024-09-06 22:05:37 -07:00
  • da915345d1
    openai: don't scale temperature or frequency_penalty (#6514) Yaroslav 2024-09-07 02:45:45 +02:00
  • 8a027bc401
    readme: add Archyve to community integrations (#6680) nickthecook 2024-09-06 17:06:01 -04:00
  • 5446903fbd
    readme: add Plasmoid Ollama Control to community integrations (#6681) imoize 2024-09-07 04:04:12 +07:00
  • 56318fb365
    Improve logging on GPU too small (#6666) Daniel Hiltgen 2024-09-06 08:29:36 -07:00
  • fe91d7fff1
    openai: fix "presence_penalty" typo and add test (#6665) frob 2024-09-06 10:16:28 +02:00
  • 608e87bf87
    Fix gemma2 2b conversion (#6645) v0.3.10-rc1 Patrick Devine 2024-09-05 17:02:28 -07:00