Commit Graph

  • 867d75b21e
    readme: add ojira to community integrations (#10648) AliAhmedNada 2025-05-10 20:36:40 +0300
  • 3fa78598a1
    cmd: strip single quotes from image page (#10636) Bruce MacDonald 2025-05-09 18:05:43 -0700
  • 0d6e35d3c6
    fix: stream accumulator exits early (#10593) Michael Yang 2025-05-08 13:17:30 -0700
  • 20c5fd39c8
    Merge branch 'main' into drifkin/array-head-count-simple Devon Rifkin 2025-05-08 11:46:52 -0700
  • 6e9a7a2568
    lint: enable usetesting, disable tenv (#10594) Michael Yang 2025-05-08 11:42:14 -0700
  • b585a58121
    chore: remove unused ZipReader type (#10621) Michael Yang 2025-05-08 11:17:41 -0700
  • 715952705e model: framework for testing forward pass brucemacd/model-forward-test-ext Bruce MacDonald 2025-05-08 09:25:12 -0700
  • fa9973cd7f
    api: remove unused sampling parameters (#10581) Jeffrey Morgan 2025-05-08 08:31:08 -0700
  • 23e8ac9428 wip? parth/python-function-parsing ParthSareen 2025-05-07 19:00:44 -0700
  • 3d9498a425 ollamarunner: Use correct constant to remove cache entries Jesse Gross 2025-05-07 17:16:07 -0700
  • 3098c8b29b
    CI: trigger downstream release process (#10508) Daniel Hiltgen 2025-05-07 10:35:12 -0700
  • 5e380c3b42
    sched: fix race leading to orphaned runners (#10599) Daniel Hiltgen 2025-05-07 09:38:17 -0700
  • 392de84031
    api: remove unused RetrieveModelResponse type (#10603) Jeffrey Morgan 2025-05-06 23:08:03 -0700
  • af31ccefc0
    fix data race in WriteGGUF (#10598) Daniel Hiltgen 2025-05-06 17:36:38 -0700
  • fa393554b9
    remove cuda v11 (#10569) Daniel Hiltgen 2025-05-06 17:33:19 -0700
  • 307e3b3e1d
    readme: add Flufy to community integrations (#9719) Aharon Bensadoun 2025-05-07 00:47:35 +0300
  • 4090aca97b
    server: send 405 instead of 404 for unallowed methods (#10275) Devon Rifkin 2025-05-06 14:45:37 -0700
  • 92ce438de0
    server: remove internal cmd (#10595) Michael Yang 2025-05-06 13:05:01 -0700
  • 424810450f
    Move quantization to new backend (#10363) Daniel Hiltgen 2025-05-06 11:20:48 -0700
  • 95e744beeb
    discover: fix compiler warnings (#10572) Michael Yang 2025-05-06 10:49:22 -0700
  • 3b2d2c8326
    api: remove unused or unsupported api options (#10574) Jeffrey Morgan 2025-05-05 14:54:40 -0700
  • d931ee8f22
    create blobs in parallel (#10135) Michael Yang 2025-05-05 11:59:26 -0700
  • a0a1fb463a build: disable cuda compression jmorganca/cuda-compression-none jmorganca 2025-05-05 10:57:28 -0700
  • 7073600797 ggml: Reduce log level of "key not found" Jesse Gross 2025-05-05 10:37:16 -0700
  • b1c40138da
    win: lint fix (#10571) Daniel Hiltgen 2025-05-05 11:08:12 -0700
  • 17466217e5
    Hide empty terminal window (#8668) Ashok Gelal 2025-05-05 21:51:46 +0545
  • 1703d1472e
    server: fix panic when runner.Options is nil (#10566) Jeffrey Morgan 2025-05-05 09:01:33 -0700
  • 913905028b
    all: fix cgo compiler warnings on windows (#10563) Jeffrey Morgan 2025-05-05 08:02:39 -0700
  • 7e5c8eee5c
    file close check and close. (#10554) 湛露先生 2025-05-05 06:37:59 +0800
  • 6a74bba7e7
    win: ensure ollama paths come first (#10549) v0.6.8-rc0 v0.6.8 Daniel Hiltgen 2025-05-03 13:11:48 -0700
  • 76ea735aaf
    sched: logging improvements (#10550) Daniel Hiltgen 2025-05-03 12:01:56 -0700
  • dd1d4e99e7
    readme: add llama 4 models (#10530) aritra saha 2025-05-03 08:15:02 +0530
  • 611d3a17ed server: add python tool parsing logic ParthSareen 2025-04-28 17:10:40 -0700
  • a6ef73f4f2 ggml: Fix race that resulted in "context canceled" when loading Jesse Gross 2025-05-01 17:06:53 -0700
  • c2f5d6662b ollamarunner: Re-enable worst case graph preallocation. Jesse Gross 2025-05-02 11:24:19 -0700
  • 57fb759f3c
    readme: update link to langchain in community integrations (#10465) Harsh Nevse 2025-05-02 11:38:51 +0530
  • 8dd12c873d
    llama: update to commit e1e8e099 (#10513) Jeffrey Morgan 2025-05-01 18:24:09 -0700
  • e6d2d04121
    image: add vision capability for projector-based models (#10509) frob 2025-05-02 01:50:20 +0200
  • 074bac8447 kvcache: Log batch size if we can't find a slot Jesse Gross 2025-05-01 13:45:32 -0700
  • 8e8f2c6d67 ollamarunner: Fix memory leak when processing images Jesse Gross 2025-05-01 11:34:02 -0700
  • 938e8447e8
    readme: add Jirapt project to community integrations (#10522) AliAhmedNada 2025-05-02 00:49:47 +0300
  • d5d5f0c445
    readme: change granite3.2 to granite3.3 (#10525) aritra saha 2025-05-02 03:16:09 +0530
  • a7835c6716
    fix: write gguf padding (#10510) v0.6.7 Michael Yang 2025-04-30 17:59:31 -0700
  • ad3c7c9bda
    strip out thinking tags in message history for qwen3 & r1 (#10490) v0.6.7-rc2 Devon Rifkin 2025-04-30 13:57:45 -0700
  • 415c8fcc3d
    Fix "Stopping..." scheduler hang (#10487) Daniel Hiltgen 2025-04-30 11:26:52 -0700
  • 718eda1b3e
    Narrow set of paths we load GGML from (#10485) Daniel Hiltgen 2025-04-30 11:25:22 -0700
  • 421b7edeb4
    readme: add link to lumina, a lightweight React frontend client (#10378) Shahin R 2025-04-30 20:20:47 +0330
  • 7b68e254c2
    all: update several golang.org/x packages (#10436) batuhankadioglu 2025-04-30 01:51:09 +0200
  • 7bec2724a5
    integration: fix embedding tests error handling (#10478) v0.6.7-rc1 Daniel Hiltgen 2025-04-29 11:57:54 -0700
  • a27462b708 ollamarunner: Temporarily disable worst case graph preallocation Jesse Gross 2025-04-29 10:48:39 -0700
  • 6bf0b8193a
    readme: fix typos (#10399) crStiv 2025-04-29 20:30:44 +0300
  • db428adbb8
    Merge pull request #10468 from ollama/drifkin/num-parallel-1 Devon Rifkin 2025-04-29 10:21:36 -0700
  • fe5b9bb21b
    lower default num parallel to 2 Devon Rifkin 2025-04-29 02:04:14 -0700
  • 67335dede2
    lower default NUM_PARALLEL to 2 drifkin/num-parallel Devon Rifkin 2025-04-29 02:03:51 -0700
  • 6ec71d8fb6
    Merge pull request #10452 from ollama/drifkin/4096-context-length Devon Rifkin 2025-04-28 17:13:51 -0700
  • 44b466eeb2 config: update default context length to 4096 Devon Rifkin 2025-04-28 17:03:23 -0700
  • a25f3f8260
    Merge pull request #10451 from ollama/revert-10364-drifkin/context-length Devon Rifkin 2025-04-28 17:02:10 -0700
  • dd93e1af85
    Revert "increase default context length to 4096 (#10364)" Devon Rifkin 2025-04-28 16:54:11 -0700
  • d20cd8df80 fix incorrect chat truncation drifkin/chat-truncation-fix Devon Rifkin 2025-04-28 16:11:36 -0700
  • d2ee599dcf load arrays with up to 1024 elements when estimating Devon Rifkin 2025-04-27 13:45:13 -0700
  • 6ed8898590 ggml: fix crash for array head counts Devon Rifkin 2025-04-25 16:16:15 -0700
  • 5cfc1c39f3
    model: fix build (#10416) v0.6.7-rc0 Michael Yang 2025-04-25 19:24:48 -0700
  • f0ad49ea17 memory Michael Yang 2025-04-23 16:20:40 -0700
  • 7ba9fa9c7d fixes for maverick Michael Yang 2025-04-21 10:45:56 -0700
  • 8bf11b84c1 chunked attention Michael Yang 2025-04-10 18:00:43 -0700
  • 470af8ab89 connect vision to text Michael Yang 2025-04-17 15:46:55 -0700
  • 178761aef3 image processing Michael Yang 2025-04-16 15:25:34 -0700
  • f0c66e6dea llama4 Michael Yang 2025-04-03 15:18:29 -0700
  • 54055a6dae fix test Michael Yang 2025-04-25 16:15:08 -0700
  • 340448d2d1 explicitly decode maxarraysize 1024 Michael Yang 2025-04-25 16:08:25 -0700
  • ced7d0e53d fix parameter count Michael Yang 2025-04-23 16:07:11 -0700
  • a0dba0f8ae default slice values Michael Yang 2025-04-23 16:05:57 -0700
  • 5e20b170a7 update comment Michael Yang 2025-04-23 15:24:20 -0700
  • d26c18e25c fix token type Michael Yang 2025-04-23 12:40:05 -0700
  • 8d376acc9b zero means zero Michael Yang 2025-04-23 12:23:21 -0700
  • dc1e81f027 convert: use -1 for read all Michael Yang 2025-04-23 12:22:02 -0700
  • 5d0279164c generic ggml.array Michael Yang 2025-04-23 11:22:06 -0700
  • 214a7678ea fix superfluous call to WriteHeader Michael Yang 2025-04-24 13:09:39 -0700
  • f4ab82f0b4 llama: sync jmorganca/sync jmorganca 2025-04-25 16:38:05 -0700
  • 4892872c18 convert: change to colmajor Michael Yang 2025-04-25 14:45:15 -0700
  • 0b9198bf47 ci: silence deprecated gpu targets warning Michael Yang 2025-03-21 15:54:49 -0700
  • b4cd1118ab checkpoint for vscode parth/python-tools-calling ParthSareen 2025-04-24 18:23:23 -0700
  • e9e5f61c45
    llama: update to commit 2016f07b (#10352) Jeffrey Morgan 2025-04-25 09:26:02 +0900
  • 128c90d3ac checkpoint!!! ParthSareen 2025-04-24 16:57:54 -0700
  • 11dde41824
    server: improve spacing for JSON grammar (#10131) Parth Sareen 2025-04-24 16:47:57 -0700
  • a53d744b01
    llama: remove model loading for grammar (#10096) Parth Sareen 2025-04-24 11:51:19 -0700
  • 40b10eee6d
    api: fix ImageData struct comment to expect raw image bytes (#10386) Adrien Duermael 2025-04-23 20:13:51 -0700
  • f5872a097c checkpoint ParthSareen 2025-04-23 15:45:35 -0700
  • 424f648632
    increase default context length to 4096 (#10364) Devon Rifkin 2025-04-22 16:33:24 -0700
  • 2eb1fb3231
    readme: add AppFlowy to community integrations (#10335) Richard Shiue 2025-04-21 06:38:06 +0800
  • 0806521642
    cmd: add support for escaping ~ in filepath (#10339) greengrass821 2025-04-21 03:51:48 +0530
  • bc73009bad guard against partially collected arrays drifkin/array-head-count-simple Devon Rifkin 2025-04-19 13:40:22 -0700
  • 731ea28aeb chunked attention mxyng/llama4 Michael Yang 2025-04-10 18:00:43 -0700
  • 778f248f8f connect vision to text Michael Yang 2025-04-17 15:46:55 -0700
  • 647d13fd81 image processing Michael Yang 2025-04-16 15:25:34 -0700
  • 7ff592460a llama4 Michael Yang 2025-04-03 15:18:29 -0700
  • 88738b357b create tempdir in models directory v0.6.6 Michael Yang 2025-04-18 16:32:48 -0700
  • 4e535e6188
    server/internal/registry: make pull send errors with Error field (#10326) Blake Mizerany 2025-04-18 18:12:28 -0700
  • 40b8fdbdca arange Michael Yang 2025-04-03 10:25:23 -0700
  • 3edbb29ef3 split pixels brucemacd/qwen25vl Bruce MacDonald 2025-04-17 16:48:50 -0700