Commit Graph

  • b7f1a395ea cmd: compact pull progress and make client2 the default bmizerany/client2progressbar Blake Mizerany 2025-03-31 17:05:22 -07:00
  • 3bc9d42e2e rebase + fix tests parth/server-enable-content-stream-with-tools ParthSareen 2025-04-03 17:23:38 -07:00
  • 4053c489b4 server: enable content streaming with tools ParthSareen 2025-03-27 14:51:39 -07:00
  • c32e71f34d change naming parth/sampling-remove-model-loading-for-grammar ParthSareen 2025-04-03 15:40:44 -07:00
  • 6bd0a983cd model: support for mistral-small in the ollama runner main Bruce MacDonald 2025-03-14 16:56:32 -07:00
  • 33d2f619b8 kvcache: stub out test structs mxyng/stub-backend Michael Yang 2025-04-03 16:54:46 -07:00
  • 3a9c7145e4 model: support for mistral-small in the ollama runner Bruce MacDonald 2025-03-14 16:56:32 -07:00
  • b38db7166d llama: shim to using ollama_vocab instead of copy ParthSareen 2025-04-03 14:58:49 -07:00
  • 1861fbdeb5
    Merge pull request #9873 from ollama/mxyng/fs-config Michael Yang 2025-04-03 14:05:21 -07:00
  • a3e03aa240 ... brucemacd/qwen25vl Bruce MacDonald 2025-04-03 13:33:19 -07:00
  • 7256d74d58 arange mxyng/arange Michael Yang 2025-04-03 10:25:23 -07:00
  • 3b96a93672 fs: move ml.Config to fs package Michael Yang 2025-03-18 14:38:44 -07:00
  • 84b326ac3e ... Bruce MacDonald 2025-04-03 12:12:09 -07:00
  • 377fa9d2ba
    cleanup Parth Sareen 2025-04-03 11:38:36 -07:00
  • ad9791da2e sample: add nil check for grammar ParthSareen 2025-04-03 11:37:51 -07:00
  • db1146f4e8 more qwen25vl qwen25omni Patrick Devine 2025-04-03 11:21:50 -07:00
  • 106592820d llama: fix naming in grammar ParthSareen 2025-04-03 11:02:13 -07:00
  • a0022981c7 server: improving grammar for JSON ParthSareen 2025-04-02 16:58:22 -07:00
  • e53b3cbd0c
    llm: set done reason at server level (#9830) Bruce MacDonald 2025-04-03 10:19:24 -07:00
  • b01b163a37 fix lint Michael Yang 2025-04-03 10:00:20 -07:00
  • 2fce80288f close temporary context Michael Yang 2025-04-03 09:59:03 -07:00
  • efa75659c3
    Update envconfig/config.go Michael Yang 2025-04-03 09:39:53 -07:00
  • 7632c4cb3c fix tests Michael Yang 2025-04-03 09:04:47 -07:00
  • 8f9eafda06 qwen25omni conversion wip Patrick Devine 2025-04-02 18:30:32 -07:00
  • 2d7e8e82ab tmp mxyng/v3 Michael Yang 2025-03-18 14:49:51 -07:00
  • c8245f3ef3 fs: move ml.Config to fs package Michael Yang 2025-03-18 14:38:44 -07:00
  • 7946618dc3 metal: op_neg Michael Yang 2025-04-02 15:28:54 -07:00
  • 0c34e82f3d vision model scaffold Bruce MacDonald 2025-04-02 16:26:59 -07:00
  • a9220da3b6 s/gelu/silu/ Michael Yang 2025-04-02 16:13:15 -07:00
  • 4948eee0d8 no projector Bruce MacDonald 2025-04-02 15:27:29 -07:00
  • a77d19454e llama: cleanup unused grammar with model loading ParthSareen 2025-04-02 15:00:10 -07:00
  • dde185b86d sample: use grammar interface without modedl loading ParthSareen 2025-04-02 14:36:44 -07:00
  • 2d64c195a2 runner: use new grammar interface ParthSareen 2025-04-02 14:36:27 -07:00
  • 486a694852 model: expose vocabulary to use for sampling ParthSareen 2025-04-02 14:30:04 -07:00
  • 92006a31a2 llama: remove model loading from grammar ParthSareen 2025-04-02 14:29:31 -07:00
  • 66f9101cb3 Update model.go Bruce MacDonald 2025-04-02 14:39:41 -07:00
  • 34fb382af9 Update model.go Bruce MacDonald 2025-04-02 14:36:19 -07:00
  • 733630a491 image processing Bruce MacDonald 2025-04-02 14:28:27 -07:00
  • b51e0f397c
    model: fix issues with spm tokenizer for Gemma 3 (#10081) v0.6.4-rc0 v0.6.4 Jeffrey Morgan 2025-04-02 13:22:56 -07:00
  • 394b69dece mistral3 quantization Michael Yang 2025-04-02 12:52:09 -07:00
  • bfdd02472c remove unused rope Michael Yang 2025-04-02 12:24:02 -07:00
  • 7465c0118e mistral3 memory Michael Yang 2025-04-02 12:11:09 -07:00
  • b42970063d kvcache: Add check for values that fall out of sliding window cache jmorganca 2025-03-30 16:05:40 -07:00
  • 87cf2fa1b8 compute image embeddings once Michael Yang 2025-04-01 16:29:35 -07:00
  • ace6176af9 restructure Bruce MacDonald 2025-04-02 10:41:51 -07:00
  • 493385eb3e ollamarunner: Don't truncate a SameBatch Jesse Gross 2025-04-01 15:01:23 -07:00
  • 159821594c
    Update ml/backend.go brucemacd/ropeconfig Bruce MacDonald 2025-04-02 09:46:19 -07:00
  • 9876c9faa4
    chore(all): replace instances of interface with any (#10067) Bruce MacDonald 2025-04-02 09:44:27 -07:00
  • 4e415029b3
    readme: add Casibase to community integrations (#10057) IsAurora6 2025-04-02 16:27:16 +08:00
  • 23267d783b ml: structured rope config to allow specifying context len Bruce MacDonald 2025-04-01 14:03:48 -07:00
  • 2ab14468a8 ml: add repeat op Michael Yang 2025-04-01 14:23:00 -07:00
  • e172f095ba
    api: return model capabilities from the show endpoint (#10066) Bruce MacDonald 2025-04-01 15:21:46 -07:00
  • cbeb2aab4f Update backend.go Bruce MacDonald 2025-04-01 15:08:59 -07:00
  • afd323d0c7 text model forward pass Bruce MacDonald 2025-04-01 14:09:41 -07:00
  • 14c8594baf ml: structured rope config to allow specifying context len Bruce MacDonald 2025-04-01 14:03:48 -07:00
  • 96df15edfc ml: structured rope config to allow specifying context len Bruce MacDonald 2025-04-01 14:03:48 -07:00
  • 90d8a1e8a2 mistral-small: use ollama engine Michael Yang 2025-04-01 13:40:36 -07:00
  • 1ca8eb5c05 use fast attention Michael Yang 2025-04-01 13:57:51 -07:00
  • 8aec3e1374 fix image embeddings Michael Yang 2025-04-01 12:20:09 -07:00
  • c001b98087
    docs: add TagSpaces to community integrations (#9983) Ilian 2025-04-01 02:28:59 +02:00
  • 23fc8e92eb
    docs: add DeepShell to community projects (#9955) Abyss-c0re 2025-04-01 03:23:04 +03:00
  • e6b561005e fix patch batch Michael Yang 2025-03-31 13:42:15 -07:00
  • 4059a297a6
    discover: /proc/cpuinfo file open and close. (#9950) 湛露先生 2025-04-01 08:07:42 +08:00
  • 6184028fc0 fix convert Michael Yang 2025-03-31 12:09:09 -07:00
  • 66b2539238
    runner: clear cache when shift is not possible (#9433) Bruce MacDonald 2025-03-31 12:54:45 -07:00
  • 557c641697 2d rope Michael Yang 2025-03-28 11:55:48 -07:00
  • ef27d52e79
    server/internal/client/ollama: cache completed chunks (#9933) Blake Mizerany 2025-03-30 23:54:54 -07:00
  • b2a465296d runner: Release semaphore and improve error messages on failures Jesse Gross 2025-03-14 17:24:46 -07:00
  • 5d097277ef ollamarunner: Ensure batch size limits are not exceeded Jesse Gross 2025-03-27 14:00:05 -07:00
  • 071a9872cb
    readme: add Writeopia to community integrations (#10042) Leandro Borges Ferreira 2025-03-31 02:28:06 +02:00
  • eb4917ceb5 model: remove verbose debug tokenizer logging jmorganca/silence-tokenizer jmorganca 2025-03-29 23:28:29 -07:00
  • 0bd0454ea7
    server: organize error types (#9465) CYJiang 2025-03-29 02:50:22 +08:00
  • 01aa788722 ml: Remove Output from Context interface Jesse Gross 2025-03-27 11:52:09 -07:00
  • e18540fecc sample: wip structured outputs work parth/sample-so-test ParthSareen 2025-03-27 11:26:49 -07:00
  • 040e65abce model: expose model vocab for structured outputs ParthSareen 2025-03-27 11:26:18 -07:00
  • ead27aa9fe
    Add gfx1200 & gfx1201 support on linux (#9878) saman-amd 2025-03-27 07:35:19 -07:00
  • b816ff86c9
    docs: make context length faq readable (#10006) Parth Sareen 2025-03-26 17:34:18 -07:00
  • e5d84fb90b
    docs: add molbal/orca-cli to community integrations (#9909) v0.6.3-rc1 v0.6.3 molbal 2025-03-26 21:39:01 +01:00
  • dd66712e31
    docs: add ollamb to community projects Hengky Steen 2025-03-27 03:38:05 +07:00
  • f66216e399 ggml: Support heterogeneous KV cache layer sizes in memory estimation Jesse Gross 2025-03-24 13:39:07 -07:00
  • f4f0992b6e llm: Fix debug logging for memory estimates Jesse Gross 2025-03-25 11:41:26 -07:00
  • 1feff61977 kvcache: Sliding window cache only needs a single batch total Jesse Gross 2025-03-24 21:17:53 -07:00
  • 4450f871db wip parth/sampling-structured-outputs ParthSareen 2025-03-25 16:45:27 -07:00
  • 564b9b48af grammar: introduce new grammar package Blake Mizerany 2024-12-11 17:50:29 -08:00
  • 5ec6bb52a0 prototyping ParthSareen 2025-03-25 15:00:14 -07:00
  • 863ba57477 fixes Michael Yang 2025-03-24 12:16:58 -07:00
  • 5e0b904e88
    docs: add flags to example linux log output command (#9852) copeland3300 2025-03-25 12:52:23 -04:00
  • 5f62064e2f examples brucemacd/doc-go-engine Bruce MacDonald 2025-03-25 09:33:17 -07:00
  • 1fd9967558 grammar: introduce new grammar package Blake Mizerany 2024-12-11 17:50:29 -08:00
  • a4265c278a wip parth/constrained-sampling-json ParthSareen 2025-02-24 17:39:01 -08:00
  • dce7cf2a1a remove debugging code Bruce MacDonald 2025-03-24 09:48:20 -07:00
  • 131f0355a5
    readme: add ollama-d library (#9907) Matheus C. França 2025-03-24 13:25:58 -03:00
  • 62108621d5 update comment jmorganca 2025-03-23 23:11:47 -07:00
  • a1c8b0fdb0 cleanup jmorganca 2025-03-23 22:49:56 -07:00
  • 3daa26e8e8 remove unneeded conversion replacement jmorganca 2025-03-23 21:57:35 -07:00
  • 1663ef289c remove large files jmorganca 2025-03-23 21:43:17 -07:00
  • 4586e137fe wip jmorganca 2025-03-23 21:41:18 -07:00
  • cfeca27133 wip jmorganca/mistral-wip jmorganca 2025-03-23 01:01:23 -07:00
  • 4530661799 wip jmorganca 2025-03-22 23:20:39 -07:00
  • 8dd2a81f8c wip jmorganca 2025-03-22 22:33:39 -07:00