mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 14:26:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 718961de68 migrate to golangci-lint v2 (#13109) Michael Yang 2025-11-18 11:00:26 -08:00
  • 330f62a7fa docs: add Void Editor to community integrations (#13124) SamareshSingh 2025-11-17 21:20:36 -06:00
  • 584e2d646f Add deepseek v3.1 (#13063) Grace 2025-11-17 18:03:21 -08:00
  • 1fd4cb87b2 app/cmd: restrict ollama:// URL scheme to supported paths (#13120) Eva H 2025-11-17 20:10:45 -05:00
  • 4aba2e8b72 discover: Support cgroups cores and memory limitations (#10292) Cerussite 2025-11-18 09:13:03 +09:00
  • 2f36d769aa bring back sysfs based VRAM information for AMD (#12871) Daniel Hiltgen 2025-11-17 15:40:58 -08:00
  • 399eacf486 ci: fix missing vulkan binaries in linux bundles (#13123) Daniel Hiltgen 2025-11-17 15:39:59 -08:00
  • 231cc878cb app/ui: fix to point ollama client to ui backend in dev mode (#13079) Eva H 2025-11-17 12:58:35 -05:00
  • aa676b313f docs: link to ollama.com instead of hardcoding list of cloud models (#13110) Jeffrey Morgan 2025-11-16 20:56:09 -08:00
  • dd0ed0ef17 docs: fix typos in repository documentation (#10683) omahs 2025-11-16 05:22:29 +01:00
  • d5649821ae readme: add Kdeps to community integrations (#11877) Joel Bryan Juliano 2025-11-16 04:19:03 +01:00
  • 4cea757e70 server: clean up manifest documentation (#12995) pierwill 2025-11-15 21:13:15 -06:00
  • a751bc159c llama: test case typo and readability improvements (#13078) Vignesh Skanda 2025-11-16 08:24:27 +05:30
  • 5d31242fbf discover: fix typos in runner.go (#13096) Laurențiu Nicola 2025-11-16 03:52:54 +01:00
  • d7fd72193f tests: basic benchmarking test framework (#12964) Patrick Devine 2025-11-15 18:17:40 -08:00
  • 72ff5b9d8c log: warn if user overrides detected (#13088) Daniel Hiltgen 2025-11-14 14:36:28 -08:00
  • ce29f695b4 docs: add logprobs to openapi (#13090) Parth Sareen 2025-11-14 14:14:58 -08:00
  • 1ce7433505 Merge branch 'ollama:main' into main v0.12.11 likelovewant 2025-11-14 16:46:05 +08:00
  • 12b174b10e fix tensor merge (#13053) Michael Yang 2025-11-13 15:32:34 -08:00
  • 333203d871 chore: update models to use slice/chunk/chunksections (#12934) Michael Yang 2025-11-13 15:20:12 -08:00
  • c114987523 logprob: add bytes to logprobs (#13068) Parth Sareen 2025-11-13 13:49:25 -08:00
  • b48083f33f ml: add slice operation (#12870) Michael Yang 2025-11-13 13:28:21 -08:00
  • 482bec824f embeddings: added cli command to embedding docs (#12993) nicole pardal 2025-11-13 13:24:13 -08:00
  • 684a9a8c5a docs: fix typo (VSCode -> VS Code) (#13072) Kowyo 2025-11-13 12:49:33 +08:00
  • 54a76d3773 app: remove source code for previous JavaScript-based macOS app (#13067) Jeffrey Morgan 2025-11-12 20:37:43 -08:00
  • 8a75d8b015 readme: add AI UI to community integrations (#13035) Radhi 2025-11-13 02:08:50 +01:00
  • f206357412 readme: fix incorrect header in community integrations (#13065) Jeffrey Morgan 2025-11-12 17:00:16 -08:00
  • 8224cd9063 ci: fix win vulkan (#13062) Daniel Hiltgen 2025-11-12 10:32:24 -08:00
  • 6286d9a3a5 Enable Vulkan with a temporary opt-in setting (#12931) Daniel Hiltgen 2025-11-12 08:40:38 -08:00
  • 3a9e8e9fd4 vulkan: temporary cary of vulkan fixes (#12971) Daniel Hiltgen 2025-11-12 08:31:40 -08:00
  • cb1cb06478 docs: rename api-reference.md back to api.md since redirect stopped working (#13056) Jeffrey Morgan 2025-11-11 15:53:06 -08:00
  • 2d5e066c8c docs: fix openapi.yaml warnings, rename api.md to api-reference.md (#12904) Jeffrey Morgan 2025-11-11 15:39:35 -08:00
  • 15968714bd docs/openapi: document that delete and copy responses are empty (#13055) Bruce MacDonald 2025-11-11 15:07:21 -08:00
  • 8bf38552de llm: Prefer dedicated GPUs over iGPUs when allocating memory Jesse Gross 2025-11-04 11:46:11 -08:00
  • b13fbad0fe llm: Separate llamaServer and ollamaServer code paths Jesse Gross 2025-11-06 10:31:08 -08:00
  • f560bd077f llm: Use Ollama engine memory layouts for both old and new engines Jesse Gross 2025-11-05 14:17:09 -08:00
  • 4372d0bfef llamarunner: Respect device ordering for offloaded layers Jesse Gross 2025-11-10 14:49:46 -08:00
  • 31361c4d3c app/ui: do not send thinking to prevent errors with cloud provider Eva H 2025-11-11 16:09:24 -05:00
  • 59241c5bee server: add logprobs and top_logprobs support to Ollama's API (#12899) Baptiste Jamin 2025-11-11 17:49:50 +01:00
  • 2a9b61f099 address comment Eva Ho 2025-11-11 08:58:55 -05:00
  • 6df4208836 docs: fix metal gpu section header (#13045) Sheikh 2025-11-11 01:51:22 -04:00
  • 9d615cdaa0 fix test Eva Ho 2025-11-10 20:13:50 -05:00
  • 6a818b8a09 clean up Eva Ho 2025-11-10 19:08:42 -05:00
  • 2aaf29acb5 app/ui: do not send to prevent errors with cloud provider Eva Ho 2025-11-10 19:05:00 -05:00
  • a42f826acb app/ui: using streamdown AI elements for markdown rendering Eva H 2025-11-10 12:05:59 -05:00
  • e10a3533a5 app/docs: remove out of date storybook instructions (#13006) Bruce MacDonald 2025-11-08 13:28:18 -08:00
  • 5580fe292c remove unnecessary files likelovewant 2025-11-08 17:41:16 +08:00
  • bbadbed1e8 fix merge conflict likelovewant 2025-11-08 17:36:08 +08:00
  • 91ec3ddbeb bugfix: don't include both consolidated.safetensors and model-*.safetensors (#13010) Patrick Devine 2025-11-07 22:41:57 -08:00
  • 755ac3b069 docs: update n8n URL for Ollama (#12994) Parth Sareen 2025-11-07 20:07:26 -08:00
  • 60b8973559 doc: re-add login autostart faq and GPU updates (#12975) Daniel Hiltgen 2025-11-07 11:21:44 -08:00
  • d2ef679d42 docs: fix 404 link to modelfile documentation (#12996) Tomoya Fujita 2025-11-08 03:06:46 +09:00
  • d4e0da0890 Remove unnecessary MacOs 13 and lower Patches (#12656) Thomas Stocker 2025-11-07 00:52:56 +01:00
  • 565b802a6b openai: fix tool call ID mapping (#12988) Jeffrey Morgan 2025-11-06 15:26:25 -08:00
  • 6c79e6c09a readme: add security tools section and Ollama fortress to community integrations (#12981) Saifeddine ALOUI 2025-11-07 00:21:13 +01:00
  • 780762f9d2 server: fix duplicate 'is' typo in comment (#12985) breatn 2025-11-06 22:44:44 +00:00
  • 30fcc71983 api: add omitempty to required tool function parameter type (#12989) Jeffrey Morgan 2025-11-06 14:08:55 -08:00
  • 3501a4bdf9 address comment Eva Ho 2025-11-06 16:49:22 -05:00
  • 73a0cafc1e Merge pull request #12973 from macarronesc/main Eva H 2025-11-06 16:31:46 -05:00
  • e309c80474 address comments Eva Ho 2025-11-06 13:49:59 -05:00
  • 544b6739dd ggml update to b6840 (#12791) Daniel Hiltgen 2025-11-06 10:19:22 -08:00
  • a4a53692f8 refactor: remove GIF support from image validation tests and logging Daniel Alejandro Coll Tejeda 2025-11-06 09:09:51 +00:00
  • c4ba257c64 readme: remove 404 link (#11351) 7394112478 2025-11-06 02:36:59 -05:00
  • 342e58ce4f readme: add hle-eval-ollama to list of terminal community integrations (#11371) mags0ft 2025-11-06 08:04:30 +01:00
  • 47b2585cfd readme: add lollms and lollms WebUI to community integrations (#11981) Saifeddine ALOUI 2025-11-06 07:48:43 +01:00
  • 4111db013f app: fix macOS file picker to support Uniform Type Identifiers (#12965) Vincent Koc 2025-11-05 21:37:17 -08:00
  • 536c987c39 address comment Eva Ho 2025-11-05 20:19:34 -05:00
  • a534d4e9e1 fixing thinking not scrolling issue Eva Ho 2025-11-05 13:12:31 -05:00
  • 74586aa9df address comments Eva Ho 2025-11-05 12:55:14 -05:00
  • 8c74f5ddfd ui: using streamdown AI elements for markdown rendering Eva Ho 2025-11-04 15:21:59 -05:00
  • 80d34260ea ci: re-enable signing (#12974) Daniel Hiltgen 2025-11-05 12:33:01 -08:00
  • bddfa2100f feat: add support for WebP images in Ollama's app Daniel Alejandro Coll Tejeda 2025-11-05 21:23:20 +01:00
  • 1ca608bcd1 embeddings: added embedding command for cl (#12795) nicole pardal 2025-11-05 11:58:03 -08:00
  • 6aa7283076 mac: fix stale VRAM data (#12972) Daniel Hiltgen 2025-11-05 11:55:17 -08:00
  • f89fc1cadd bugfix: show connection string for interactive cli usage (#12930) Patrick Devine 2025-11-05 11:55:04 -08:00
  • 97e05d2a6b win: revert CPU discovery logic to 0.12.3 (#12969) Daniel Hiltgen 2025-11-05 10:32:38 -08:00
  • 8bbc7395db readme: Add handy-ollama to community integrations (#8601) Youdon 2025-11-06 01:56:14 +08:00
  • 408c2f99d0 log: trace logging for scheduler (#12961) Daniel Hiltgen 2025-11-05 08:12:15 -08:00
  • 809b9c68fa Add Tool Call ID (#12956) Grace 2025-11-04 16:43:33 -08:00
  • ba8c035846 log: instrument CPU discovery timing (#12960) Daniel Hiltgen 2025-11-04 16:23:37 -08:00
  • 27f1fde413 discovery: only retry AMD GPUs (#12894) Daniel Hiltgen 2025-11-04 15:33:46 -08:00
  • 220e133fca vulkan: Add memory detection for Intel GPU using DXGI+PDH (#12664) virajwad 2025-11-04 15:11:55 -07:00
  • d3b4b9970a app: add code for macOS and Windows apps under 'app' (#12933) Daniel Hiltgen 2025-11-04 11:40:17 -08:00
  • a4770107a6 vulkan: enable flash attention (#12937) Daniel Hiltgen 2025-11-04 10:31:22 -08:00
  • ef549d513c ggml: Increase maximum graph size Jesse Gross 2025-10-30 14:30:31 -07:00
  • d2158ca6f4 readme: add Hillnote to community integrations (#12929) Rajath Bail 2025-11-04 02:25:04 +05:30
  • ce3eb0a315 chore(gptoss): cleanup dead code (#12932) Michael Yang 2025-11-03 11:27:15 -08:00
  • 60829f7ec6 readme: add Strands Agents to community integrations (#11740) Ryan Coleman 2025-11-02 16:01:28 -08:00
  • 9a50fd584c readme: add Ollama Bash Lib to community integrations (#12235) Attogram Project 2025-11-03 00:44:56 +01:00
  • 392a270261 ggml: Avoid cudaMemsetAsync during memory fitting Jesse Gross 2025-10-31 14:16:20 -07:00
  • 3bee3af6ed cpu: always ensure LibOllamaPath included (#12890) Daniel Hiltgen 2025-10-31 14:37:29 -07:00
  • 83537993d7 logs: catch rocm errors (#12888) Daniel Hiltgen 2025-10-31 09:54:25 -07:00
  • 0f03e90f89 fix CMakePresets.json likelovewant 2025-10-31 15:46:38 +08:00
  • 58b175b6b1 fix CMakePresets.json likelovewant 2025-10-31 15:45:07 +08:00
  • c9f83eaa98 Merge branch 'ollama:main' into main likelovewant 2025-10-31 14:12:02 +08:00
  • 7dd4862a89 embeddings: removed redundant TestAPIEmbeddings test (#12863) nicole pardal 2025-10-30 17:12:33 -07:00
  • db973c8fc2 win: avoid ID mixups on refresh (#12869) Daniel Hiltgen 2025-10-30 15:12:14 -07:00
  • afaf7ce8c3 ggml: Enable op_offload to improve partial offload performance Jesse Gross 2025-10-27 16:32:05 -07:00
  • 26465fb85f ollamarunner: Worst case batch for token generation Jesse Gross 2025-10-27 16:31:58 -07:00
  • 88236bc05f win: use copy for subprocess logs (#12864) Daniel Hiltgen 2025-10-30 13:22:00 -07:00