Commit Graph

  • 5d8c173529 readme: add NativeMind to community integrations (#11242) main XuKecheng 2025-07-02 00:46:15 +08:00
  • 44b17d2bfa tools: fix parsing tool calls with empty arguments, missing required fields (#11233) v0.9.4-rc6 v0.9.4-rc5 v0.9.4-rc4 v0.9.4-rc3 v0.9.4 Jeffrey Morgan 2025-06-30 08:59:03 -07:00
  • 3b8b692218 readme: add ollama-bash-toolshed to community integrations (#11224) Attogram Project 2025-06-29 23:59:54 +02:00
  • 3e5996df67 Revert "ggml: Temporarily disable reporting UUIDs" jessegross/revert Jesse Gross 2025-06-27 16:19:44 -07:00
  • 4129af9205 chore: cleanup comments + unused vars (#11225) v0.9.4-rc2 v0.9.4-rc1 Michael Yang 2025-06-27 11:45:33 -07:00
  • 45f216a9c7 ggml: Temporarily disable reporting UUIDs Jesse Gross 2025-06-27 11:11:49 -07:00
  • d0b32def60 skip quantizing per_layer_token_embd (#11207) Michael Yang 2025-06-26 21:49:35 -07:00
  • 5f19295def llmserver jessegross/memory Jesse Gross 2025-05-29 12:21:48 -07:00
  • 5545c27aad backend close Jesse Gross 2025-04-17 17:12:01 -07:00
  • 4bae682ef9 uuid Jesse Gross 2025-06-25 17:13:32 -07:00
  • 11ffc36157 ci: multi-stage release process (#11001) v0.9.4-rc0 Daniel Hiltgen 2025-06-26 10:32:48 -07:00
  • ba04902670 fs/ggml: add multiplier in graph estimates (#11208) v0.9.3 Jeffrey Morgan 2025-06-26 00:19:44 -07:00
  • 3944602f51 fs/ggml: add missing architecture to OllamaEngineRequired() (#11206) Jeffrey Morgan 2025-06-26 00:11:23 -07:00
  • 3d6ad58968 remove extra field attr mxyng/cleanup Michael Yang 2025-06-25 21:30:09 -07:00
  • 73b642e6f3 add new gemma model (#11204) v0.9.3-rc5 Michael Yang 2025-06-25 21:47:09 -07:00
  • 46fe4938f3 ci: multi-stage release process v0.9.4-citest0 Daniel Hiltgen 2025-06-05 10:42:55 -07:00
  • ad118d8b13 ci: arm sbsa fixes (#11194) v0.9.3-rc4 Daniel Hiltgen 2025-06-24 21:00:15 -07:00
  • f08534137b ci: include dependencies v0.9.3-rc3 Daniel Hiltgen 2025-06-24 20:27:43 -07:00
  • 4b4a90f233 ci: pick up arm sbsa cuda libs (#11192) v0.9.3-rc2 Daniel Hiltgen 2025-06-24 18:59:22 -07:00
  • 03274a6b2f ci: recombine linux amd64 binaries (#11188) Daniel Hiltgen 2025-06-24 18:45:01 -07:00
  • cc6463ebca Merge pull request #10238 from ollama/drifkin/array-head-count-simple Devon Rifkin 2025-06-24 17:50:02 -07:00
  • 405d2f628f ci: rocm parallel builds on windows (#11187) Daniel Hiltgen 2025-06-24 15:27:09 -07:00
  • a3f7dd3e98 Merge branch 'main' into drifkin/array-head-count-simple Devon Rifkin 2025-06-24 14:20:05 -07:00
  • c85c0ebf89 CI: switch windows to vs 2022 (#11184) v0.9.3-rc1 Daniel Hiltgen 2025-06-24 13:26:55 -07:00
  • 10a8e04a8d avoid context overflow (#11175) v0.9.3-rc0 Daniel Hiltgen 2025-06-23 15:52:50 -07:00
  • 1c6669e64c Re-remove cuda v11 (#10694) Daniel Hiltgen 2025-06-23 14:07:00 -07:00
  • b2b270ad5d Merge branch 'main' into drifkin/array-head-count-simple Devon Rifkin 2025-06-23 10:37:31 -07:00
  • 2bb69b40c7 readme: add ai-hub to community integrations (#11169) AJ 2025-06-23 21:51:12 +05:30
  • 65bff664cb build speedups (#11142) Daniel Hiltgen 2025-06-20 12:32:51 -07:00
  • 7e0602fefd lazy gguf arrays mxyng/gguf Michael Yang 2025-06-12 10:57:17 -07:00
  • 99f3db95c7 benchmark tests Michael Yang 2025-06-12 10:56:23 -07:00
  • c088ac0e79 convert: utility for merging tensors (#11069) Michael Yang 2025-06-20 11:12:01 -07:00
  • 0a066cfd91 Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119) Michael Yang 2025-06-20 11:11:40 -07:00
  • 87b7af6cee ggml: Check return status for computation. Jesse Gross 2025-06-19 14:39:20 -07:00
  • f2527b08fb int: add coverage for older models (#11137) Daniel Hiltgen 2025-06-19 12:10:19 -07:00
  • beaa0e82f3 api: add flag to disable context shifting parth/opt-in-error-context-window ParthSareen 2025-06-18 17:51:14 -07:00
  • 8bcb3125c1 benchmark: remove unused benchmark test (#11120) Jeffrey Morgan 2025-06-18 12:58:50 -07:00
  • 6baf1e31e2 Revert "Revert "ggml: Export GPU UUIDs" (#11115)" (#11117) Jeffrey Morgan 2025-06-18 07:30:49 -07:00
  • ed567ef43b Revert "ggml: Export GPU UUIDs" (#11115) v0.9.2 Jeffrey Morgan 2025-06-18 05:45:00 -07:00
  • a6e64fbdf2 Revert "feat: incremental gguf parser (#10822)" (#11114) Jeffrey Morgan 2025-06-18 05:42:44 -07:00
  • 60cfa2a203 cache: fix comment function name in cache.go (#11110) 曹家巧 2025-06-18 20:21:45 +08:00
  • 55bbf3b4a1 tools: return empty arguments object instead of null (#11113) Jeffrey Morgan 2025-06-18 05:20:43 -07:00
  • 6bda1d2479 tools: fix parsing tool calls without any parameters (#11101) Jeffrey Morgan 2025-06-17 10:51:43 -07:00
  • f2a4d058f9 gofmt brucemacd/cache-models Bruce MacDonald 2025-06-16 16:34:46 -07:00
  • 63e7634014 pr feedback Bruce MacDonald 2025-06-16 16:08:38 -07:00
  • 9e125d884c model: treat 'user defined' tokens as special tokens (#11077) Jeffrey Morgan 2025-06-16 16:03:16 -07:00
  • 8d51d92f3b server: cache gguf model capabilities rather than reading off disc Bruce MacDonald 2025-06-11 11:28:40 -07:00
  • 2348fef568 Revert "server: model info caching system for improved performance" Bruce MacDonald 2025-06-11 11:04:33 -07:00
  • 883f655dd6 server: model info caching system for improved performance Bruce MacDonald 2025-06-10 16:10:13 -07:00
  • a6fbfc880c gguf: fix write order (#11068) Michael Yang 2025-06-16 10:42:32 -07:00
  • 502028968d readme: add ollama-launcher to community integrations (#11080) NGC13009 2025-06-16 12:27:49 +08:00
  • 5a8eb0e151 readme: add GPTranslate to community integrations (#11071) v0.9.1 Phil 2025-06-14 17:54:03 +02:00
  • d5eae8248d runner: enable returning more info from runner processing brucemacd/runner-completion Bruce MacDonald 2025-02-21 16:31:31 -08:00
  • 9f8a18ec05 tools: loosen tool parsing to allow for more formats (#11030) v0.9.1-rc1 Jeffrey Morgan 2025-06-12 14:18:54 -07:00
  • 6b04cad7e8 feat: incremental gguf parser (#10822) Michael Yang 2025-06-12 11:04:11 -07:00
  • 45f56355d5 feat: uneven splits (#11048) Michael Yang 2025-06-11 12:10:54 -07:00
  • 0dabb4ef6a skip tokenizer.model if possible (#11050) Michael Yang 2025-06-11 12:10:35 -07:00
  • 2e77aa1ae7 use nn.Linear in place of ml.Tensor (#11049) Michael Yang 2025-06-11 12:10:15 -07:00
  • deaabe292d readme: add ollama-multirun to community integrations (#11038) Attogram Project 2025-06-10 23:14:51 +02:00
  • af21a5ac39 readme: update quickstart link text to Gemma 3 Jeffrey Morgan 2025-06-10 09:34:23 -07:00
  • f63d7f68eb readme: update quickstart example to Gemma 3 Jeffrey Morgan 2025-06-10 09:33:54 -07:00
  • 82ad1dbc07 mac: handle "keep" named apps (#11031) Daniel Hiltgen 2025-06-09 16:29:57 -07:00
  • feeabdadd2 spawn desktop quickly (#11011) v0.9.1-rc0 Daniel Hiltgen 2025-06-08 09:34:52 -07:00
  • f5d663e370 update patches jmorganca/llama-update-6 jmorganca 2025-06-07 12:36:59 -04:00
  • e5209778f1 llama: update vendored code to commit 1caae7fc6c77551cb1066515e0f414713eebb367 jmorganca 2025-06-07 12:32:55 -04:00
  • fc0309615e docs: update link to AMD drivers in linux.md (#10973) Krzysztof Jeziorny 2025-06-07 05:30:04 +02:00
  • 09d308d6b6 Revert "server: add model capabilities to the list endpoint (#10174)" (#11004) Jeffrey Morgan 2025-06-06 23:29:14 -04:00
  • 46faf61a14 ... brucemacd/benchmark-list Bruce MacDonald 2025-06-06 16:34:53 -07:00
  • 3cf62838ce server: do partial gguf kv read for capability check brucemacd/partial-read-caps Bruce MacDonald 2025-06-06 15:51:38 -07:00
  • 22aed78048 Update gguf_test.go Bruce MacDonald 2025-06-06 15:20:43 -07:00
  • d3cbbbfd85 more type conversions Bruce MacDonald 2025-06-06 15:17:22 -07:00
  • e8d1933b99 fix lint unneeded conversions Bruce MacDonald 2025-06-06 15:05:09 -07:00
  • 735e80787b gguf: update test to not rely on gguf on disc Bruce MacDonald 2025-06-06 14:38:50 -07:00
  • 8e3998b9dd wip: incremental gguf parser Michael Yang 2025-05-09 09:52:02 -07:00
  • a8ed68bd93 launch app hidden (#10962) Daniel Hiltgen 2025-06-06 14:06:29 -07:00
  • 2ae65ae471 win: handle more than 2048 processes (#10997) Daniel Hiltgen 2025-06-06 14:06:09 -07:00
  • a3b6886b7d move thinking logic into its own package (#10990) Devon Rifkin 2025-06-06 12:02:20 -07:00
  • c6a6d7294d docs: fix typo in development.md (#10998) Hunter Wittenborn 2025-06-06 11:07:29 -05:00
  • 2cf007c9d1 Merge pull request #10987 from ollama/drifkin/export-thinking-parser Devon Rifkin 2025-06-05 12:19:14 -07:00
  • 0683efa637 export ThinkingParser Devon Rifkin 2025-06-05 10:22:32 -07:00
  • 0943001193 server: add model capabilities to the list endpoint (#10174) JasonHonKL 2025-06-05 02:39:48 +08:00
  • 5c42800fca readme: add SimpleOllamaUnity to community integrations (#10817) HardCodeDev 2025-05-31 06:50:16 +04:00
  • 65f10c2823 tools: resiliency upgrade to name and arg extraction from template (#10917) Parth Sareen 2025-05-30 15:18:09 -07:00
  • 478824045d temp parth/deepseek-r1-tools ParthSareen 2025-05-29 15:26:37 -07:00
  • aaa7818000 ggml: Export GPU UUIDs Jesse Gross 2025-04-24 11:48:49 -07:00
  • f15ffc4320 llm: Make "POST predict" error message more informative Jesse Gross 2025-05-13 17:26:46 -07:00
  • 5f57b0ef42 add thinking support to the api and cli (#10584) v0.9.0-rc0 v0.9.0 Devon Rifkin 2025-05-28 19:38:52 -07:00
  • aa25aff10d client: add request signing to the client (#10881) v0.8.0 Patrick Devine 2025-05-27 16:50:57 -07:00
  • ea79003180 kvcache: Skip computing causal mask for worst case graph reservation Jesse Gross 2025-05-27 13:33:57 -07:00
  • 9239a254e0 server: abort download on empty digest Kyle Steere 2025-05-27 18:28:48 +00:00
  • 066d0f4746 tools: relax JSON parse constraints for tool calling (#10872) v0.8.0-rc0 Parth Sareen 2025-05-26 18:59:06 -07:00
  • aea6fb9b58 tools: remove newline stripping (#10869) Parth Sareen 2025-05-26 17:16:00 -07:00
  • 012cf65340 readme: add AWS Strands Agents SDK example to community integrations (#10865) RAPID ARCHITECT 2025-05-26 14:05:03 -05:00
  • a45231af47 readme: Add macLlama to community integrations (#10790) Min Yoo 2025-05-25 05:18:32 +09:00
  • 2307fc2bcd tests: drop llama3.2-vision embedding tests (#10837) Daniel Hiltgen 2025-05-24 13:17:53 -07:00
  • 6623898198 docs: remove unsupported quantizations (#10842) frob 2025-05-24 22:17:26 +02:00
  • eda472df1b server: add hint to the error message when model path access fails (#10843) frob 2025-05-24 22:17:04 +02:00
  • f18e0cb550 ml: Improve slog formatting for BackendMemory Jesse Gross 2025-05-23 15:37:32 -07:00
  • e8b981fa5d tools: refactor tool call parsing and enable streaming (#10415) Parth Sareen 2025-05-23 14:19:31 -07:00
  • 884d26093c llama: add minimum memory for grammar (#10820) v0.7.1-rc2 v0.7.1 Parth Sareen 2025-05-22 18:53:31 -07:00