Commit graph

  • 5b3393b6a2 fix(mllama): sync backend between batches Michael Yang 2024-11-13 14:12:30 -0800
  • d7eb05b936 runner.go: Fix off-by-one for num predicted Jesse Gross 2024-11-12 10:41:44 -0800
  • 636a743c2b
    CI: give windows lint more time () Daniel Hiltgen 2024-11-12 11:22:39 -0800
  • df011054fa
    Jetpack support for Go server () Daniel Hiltgen 2024-11-12 10:31:52 -0800
  • ac07160c8d
    doc: capture numeric group requirement () Daniel Hiltgen 2024-11-12 09:13:23 -0800
  • 6606e4243c
    docs: Capture docker cgroup workaround () Daniel Hiltgen 2024-11-12 09:12:50 -0800
  • 65973ceb64 runner.go: Make KV entry accounting more robust Jesse Gross 2024-11-08 11:10:56 -0800
  • bebef1e50d
    readme: add aichat terminal app to community integrations () Joey Zheng 2024-11-12 08:44:46 +0800
  • d48c1c5a44
    api: fix typos in Go Doc comments () Evan 2024-11-11 16:21:58 -0800
  • 36a8372b28
    readme: add GoLamify to community integrations () Prasad Bhalerao 2024-11-11 12:08:18 +0530
  • 4e94227b5d
    readme: add browser extension that enables using Ollama for interacting with web pages () Ivo Stoykov 2024-11-11 06:14:22 +0000
  • 479d551766
    docs: add mentions of Llama 3.2 () frances720 2024-11-10 19:04:23 -0800
  • 76b2b723b2
    api: fix typo in python ClientFromEnvironment docs () Evan 2024-11-10 17:30:27 -0800
  • b8d77cdeab
    readme: add llama3.2-vision to model list () Arhan Busam 2024-11-11 08:36:25 +1100
  • 6196829bb9
    Fix the prompt baalajimaestro 2024-11-10 23:51:37 +0530
  • aa3a7dea34
    Merge https://github.com/ollama/ollama baalajimaestro 2024-11-10 22:43:23 +0530
  • c2e8cbaa14 runner.go: Check for zero length images Jesse Gross 2024-11-06 13:14:18 -0800
  • 771fab1dd8
    docs: update langchainpy.md with proper model name () Edward J. Schwartz 2024-11-08 12:36:17 -0500
  • 3a5239e6bf
    Set macos min version for all architectures () Daniel Hiltgen 2024-11-08 09:27:04 -0800
  • 3d25e7bf8c
    win: remove preview title from installer () Daniel Hiltgen 2024-11-07 14:26:47 -0800
  • 1618700c5a
    Workaround buggy P2P ROCm copy on windows () Daniel Hiltgen 2024-11-07 14:26:31 -0800
  • b111aa5a91
    Debug logging for nvcuda init () Daniel Hiltgen 2024-11-07 14:25:53 -0800
  • 9e83e550e1
    Align rocm compiler flags () Daniel Hiltgen 2024-11-07 10:20:50 -0800
  • fc2a0715df
    Be explicit for gpu library link dir () Daniel Hiltgen 2024-11-07 09:20:40 -0800
  • 3020d2dc58 docs: OLLAMA_NEW_RUNNERS no longer exists Jesse Gross 2024-11-06 13:38:57 -0800
  • a909417602 runner.go: Remove unused arguments Jesse Gross 2024-10-30 16:54:49 -0700
  • 6cd566872b sched: Lift parallel restriction for multimodal models except mllama Jesse Gross 2024-10-30 17:09:42 -0700
  • 9d71bcc3e2
    Update README.md () RAPID ARCHITECT 2024-11-05 17:07:25 -0600
  • a4c70fe157
    One corrupt manifest should not wedge model operations () Daniel Hiltgen 2024-11-05 14:21:45 -0800
  • 34a75102f7 prompt: Use a single token when estimating mllama context size Jesse Gross 2024-11-04 17:30:20 -0800
  • 4157d1f7b6
    readme: add Hexabot to the list of community integrations Med Marrouchi 2024-11-05 18:06:38 +0100
  • 4ebfa2cb91
    Quiet down debug log of image payload () Daniel Hiltgen 2024-11-04 13:05:16 -0800
  • 046054fa3b
    CI: Switch to v13 macos runner () Daniel Hiltgen 2024-11-04 13:02:07 -0800
  • 95483f348b
    CI: matrix strategy fix () Daniel Hiltgen 2024-11-04 10:48:35 -0800
  • f247a6233e
    Merge pull request from ollama/mxyng/llama3.2-vision-mem Michael Yang 2024-11-04 09:48:43 -0800
  • 44bd9e5994
    Sign windows arm64 official binaries () Daniel Hiltgen 2024-11-04 09:15:14 -0800
  • 18237be9b2
    readme: add TextCraft to community integrations () suncloudsmoon 2024-11-03 16:53:51 -0800
  • 29ab9fa7d7
    nvidia libs have inconsistent ordering () Daniel Hiltgen 2024-11-02 16:35:41 -0700
  • b8d5036e33
    CI: omit unused tools for faster release builds () Daniel Hiltgen 2024-11-02 13:56:54 -0700
  • 312d9de1d1 llama: Improve error handling Jesse Gross 2024-11-01 15:50:53 -0700
  • a103dae01e runner.go: Only allocate 1 element embedding batches for mllama Jesse Gross 2024-11-01 14:29:57 -0700
  • d07cf41a97 refactor kv estimation Michael Yang 2024-10-31 13:46:30 -0700
  • 8c238e70ab mllama cross attention Michael Yang 2024-10-31 13:40:06 -0700
  • 8a9bb0d000
    Add basic mllama integration tests () Daniel Hiltgen 2024-10-31 17:25:48 -0700
  • 26acdcf44e runner.go: Don't set cross attention before sending embeddings Jesse Gross 2024-10-31 10:55:31 -0700
  • 921779bb10
    Give unicode test more time to run () Daniel Hiltgen 2024-10-31 13:35:31 -0700
  • 16f4eabe2d
    Refine default thread selection for NUMA systems () Daniel Hiltgen 2024-10-30 15:05:45 -0700
  • c826e57475 runner.go: Better abstract vision model integration Jesse Gross 2024-10-11 15:34:01 -0700
  • 712e99d477
    Soften windows clang requirement () Daniel Hiltgen 2024-10-30 12:28:36 -0700
  • b754f5a6a3
    Remove submodule and shift to Go server - 0.4.0 () Daniel Hiltgen 2024-10-30 10:34:28 -0700
  • a805e5947e
    Move windows app out of preview () Daniel Hiltgen 2024-10-30 09:24:59 -0700
  • 91dfbb1bba
    windows: Support alt install paths, fit and finish () Daniel Hiltgen 2024-10-30 09:24:31 -0700
  • db1842b9e1
    add more tests for getting the optimal tiled canvas () Patrick Devine 2024-10-29 16:28:02 -0700
  • c9ca386131
    Switch windows to clang () Daniel Hiltgen 2024-10-29 13:15:04 -0700
  • 77dfd8ba16
    Merge https://github.com/ollama/ollama baalajimaestro 2024-10-29 22:50:58 +0530
  • 078f666f73 tests: Add test for Unicode processing Jesse Gross 2024-10-23 15:28:30 -0700
  • de1557a0dc runner.go: Better handle return NULL values from llama.cpp Jesse Gross 2024-10-22 14:57:46 -0700
  • 084929c293
    add mllama image processing to the generate handler () Patrick Devine 2024-10-28 13:51:19 -0700
  • abd5dfd06a
    Bump to latest Go 1.22 patch () Daniel Hiltgen 2024-10-26 17:03:37 -0700
  • 099f7077a1
    Fix deepseek deseret regex () Daniel Hiltgen 2024-10-26 14:58:54 -0700
  • d7c94e0ca6
    Better support for AMD multi-GPU on linux () Daniel Hiltgen 2024-10-26 14:04:14 -0700
  • 35ec7f079f
    Fix unicode output on windows with redirect to file () Daniel Hiltgen 2024-10-25 13:43:16 -0700
  • 5231ae52d9
    Fix incremental build file deps () Daniel Hiltgen 2024-10-25 11:50:45 -0700
  • 3085c47bea
    Improve dependency gathering logic () Daniel Hiltgen 2024-10-24 09:51:53 -0700
  • 0ccc73251a
    fix - invalid image input () Bill Wang 2024-10-24 04:31:04 +1100
  • dc6fe82051
    integration: harden embedding test () Daniel Hiltgen 2024-10-22 15:25:22 -0700
  • d78fb62056
    default to "FROM ." if a Modelfile isn't present () Patrick Devine 2024-10-22 13:32:24 -0700
  • 5c44461ccf
    Fix rocm windows build and clean up dependency gathering () Daniel Hiltgen 2024-10-22 12:54:15 -0700
  • 03e40efa51 runner.go: Merge partial unicode characters before sending Jesse Gross 2024-10-21 11:07:19 -0700
  • 23f746508d
    readme: add Ollama for Swift to the community integrations () Mattt 2024-10-21 22:29:11 -0700
  • 48708ca0d5
    server: allow vscode-webview origin () Jeffrey Morgan 2024-10-19 17:06:41 -0400
  • c7cb0f0602
    image processing for llama3.2 () Patrick Devine 2024-10-18 16:12:35 -0700
  • bf4018b9ec
    llama: Decouple patching script from submodule () Daniel Hiltgen 2024-10-17 15:03:09 -0700
  • f86d00cd95
    llama: add compiler tags for cpu features () Daniel Hiltgen 2024-10-17 13:43:20 -0700
  • f2890a4494
    IBM granite/granitemoe architecture support () Gabe Goodhart 2024-10-17 12:59:52 -0600
  • 05cd82ef94
    Rename gpu package discover () Daniel Hiltgen 2024-10-16 17:45:00 -0700
  • 7d6eb0d4c3
    Move macos v11 support flags to build script () Daniel Hiltgen 2024-10-16 12:49:46 -0700
  • 24636dfa87
    Discovery CPU details for default thread selection () Daniel Hiltgen 2024-10-15 11:36:08 -0700
  • 1d7fa3ad2d
    Adding 'Ollama App' as community integrations () JHubi1 2024-10-15 18:57:32 +0200
  • 1134287d38
    Merge https://github.com/ollama/ollama baalajimaestro 2024-10-15 16:19:26 +0530
  • 09035b71cd
    Add missing BF16 tensor type. () frob 2024-10-15 02:06:35 +0200
  • f3c8b898cd
    Track GPU discovery failure information () Daniel Hiltgen 2024-10-14 16:26:45 -0700
  • 5dd0477fd4
    Fix regression on older macos versions () Daniel Hiltgen 2024-10-13 10:47:42 -0700
  • c3d321d405
    llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm () Daniel Hiltgen 2024-10-12 09:56:49 -0700
  • 7fe3902552 cli: Send all images in conversation history Jesse Gross 2024-10-09 20:46:27 -0700
  • 42ae547a39
    Merge https://github.com/ollama/ollama baalajimaestro 2024-10-10 21:11:43 +0530
  • 0077e22d52 runner.go: Handle truncation of tokens for stop sequences Jesse Gross 2024-10-09 16:12:23 -0700
  • 03408f3437 server: Don't clear cmd when closing a server Jesse Gross 2024-10-09 16:55:34 -0700
  • cd7e01e8b9
    fix vendoring attribute for metal () Daniel Hiltgen 2024-10-09 15:22:36 -0700
  • 7a962bd802
    fix vendoring attribute () Daniel Hiltgen 2024-10-09 14:21:02 -0700
  • f9584deba5
    Fix build leakages () Daniel Hiltgen 2024-10-08 13:04:59 -0700
  • 96efd9052f
    Re-introduce the llama package () Jeffrey Morgan 2024-10-08 11:53:54 -0400
  • de982616f1
    readme: replace stale links to LangChain documentation () Shifra Goldstone 2024-10-07 21:16:56 -0400
  • defbf9425a
    readme: add G1 to list of community integrations () hidden1nin 2024-10-05 14:57:53 -0400
  • f40bb398f6
    Stop model before deletion if loaded (fixed ) () Alex Mavrogiannis 2024-10-01 15:45:43 -0700
  • 79d3b1e2bd
    readme: add ARGO LLM tool to community integrations () zmldndx 2024-09-30 04:01:01 +0800
  • 9fb5f4446a
    Merge https://github.com/ollama/ollama baalajimaestro 2024-09-29 15:01:23 +0530
  • 03608cb46e
    server: close response body on error () Blake Mizerany 2024-09-26 12:00:31 -0700
  • 450acb71a6
    readme: fix llama3.1 -> llama3.2 typo () Xe Iaso 2024-09-25 11:53:47 -0700
  • 55ea963c9e
    update default model to llama3.2 () Jeffrey Morgan 2024-09-25 11:11:22 -0700