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

  • cbb2f09129 Merge branch 'ollama:main' into main main v0.13.5 likelovewant 2025-12-19 19:18:33 +08:00
  • 8852220f59 add REQUIRES command to Modelfile (#13361) Jeffrey Morgan 2025-12-18 13:21:29 -08:00
  • 7325791599 parsers/renderers: functiongemma (#13521) Parth Sareen 2025-12-18 07:55:37 -08:00
  • 522c11a763 Revert "Omit args and params in tool function def and calls (#13516)" (#13518) Grace 2025-12-17 19:06:56 -08:00
  • 0fadeffaee Omit args and params in tool function def and calls (#13516) Grace 2025-12-17 18:42:21 -08:00
  • 49a9c9ba6a GGML update to ec98e2002 (#13451) Daniel Hiltgen 2025-12-17 13:13:55 -08:00
  • 1c094038bc types: add nested property support for tool definitions (#13508) Parth Sareen 2025-12-17 11:54:09 -08:00
  • a013693f80 DeepseekV3 Family Parser (#13484) Grace 2025-12-16 18:56:30 -08:00
  • f6a016f49d revert granite-embedding (#13505) Michael Yang 2025-12-16 15:44:52 -08:00
  • 45c4739374 types: ConfigV2 and RootFS (#13504) Bruce MacDonald 2025-12-16 15:18:17 -08:00
  • 2dd029de12 remove unnecessary code (#13502) Michael Yang 2025-12-16 15:11:26 -08:00
  • 903b1fc97f use ollama engine for bert models (#13501) Michael Yang 2025-12-16 11:29:19 -08:00
  • 89eb795293 parsers/renderers: use think from user for nemotron (#13492) Parth Sareen 2025-12-15 18:55:17 -08:00
  • 7e3ea813c1 llama/parsers/renderers: nemotron 3 nano (#13489) Parth Sareen 2025-12-15 18:00:08 -08:00
  • 7b95087b9d Adding tool definitions to DeepseekV3 renderer (#13491) Grace 2025-12-15 17:57:06 -08:00
  • 971d62595a fix: qwen2.5 vl rope (#13486) Michael Yang 2025-12-15 17:30:33 -08:00
  • ffbe8e076d model: add olmo3 and olmo3.1 (#13415) Parth Sareen 2025-12-15 15:20:04 -08:00
  • 2c639431b1 DeepseekV3 family renderer (#13180) Grace 2025-12-15 14:50:52 -08:00
  • aacd1cb394 fix: define GGML_VERSION variables for proper SOVERSION expansion (#13469) Nhan Nguyen 2025-12-15 17:42:15 -05:00
  • e3731fb160 renderers: add olmo3.1 and olmo3 fixes (#13447) Parth Sareen 2025-12-15 11:26:43 -08:00
  • 8dbc9e7b68 app/ui: handle unspecified bind addresses and wait for server in ollama proxy (#13159) Eva H 2025-12-15 13:33:09 -05:00
  • abe67acf8a Revert "Enable Ollama engine by default" (#13481) Daniel Hiltgen 2025-12-15 09:55:45 -08:00
  • ff2011376d Merge branch 'ollama:main' into main v0.13.3 likelovewant 2025-12-14 18:55:05 +08:00
  • 4ff8a691bc model: default gemma 3 rope scale to 1.0, apply corrections based on layer counts (#13453) Jeffrey Morgan 2025-12-12 17:51:56 -08:00
  • 1b308e1d2a model: fix global layer rope scale values for gemma 3 (#13452) Jeffrey Morgan 2025-12-12 16:29:01 -08:00
  • bd6c1d6b49 flash attn: add auto mode for llama engine (#13052) Daniel Hiltgen 2025-12-12 13:27:19 -08:00
  • 3af5d3b738 model: force rope factor 1.0 for Gemma 3 (#13445) Jeffrey Morgan 2025-12-12 13:27:08 -08:00
  • 7730895158 Enable Ollama engine by default (#13443) Daniel Hiltgen 2025-12-12 11:48:43 -08:00
  • de9ecfd01c tidy up lint warnings on windows (#13430) Eva H 2025-12-12 11:43:35 -05:00
  • 95fdd8d619 fix: select and update models folder in settings (#13412) Eva H 2025-12-12 11:09:37 -05:00
  • 9f7822851c docs: add docs for v1/responses and rework openai compat section (#13416) Devon Rifkin 2025-12-11 17:39:40 -08:00
  • 9b2035d194 openai: add tool call appending to previous assistant message (#13434) Parth Sareen 2025-12-11 17:30:12 -08:00
  • 93d45d7a04 docs: fix link to modelfile.mdx (#13220) Alexander Gusak 2025-12-12 00:14:45 +00:00
  • 709f842457 Update README.md (#13373) JJ 2025-12-11 16:08:57 -08:00
  • 2dfb74410d model: fix rotary embeddings for ministral 3 (#13432) Jeffrey Morgan 2025-12-11 16:02:05 -08:00
  • 1eb5e75972 openai: add v1/responses support (#13351) Devon Rifkin 2025-12-11 15:37:10 -08:00
  • 3475d915cb embeddings: modified batch size (#13429) nicole pardal 2025-12-11 15:36:31 -08:00
  • 48e78e9be1 template: add yesterdayDate helper function (#13431) Jeffrey Morgan 2025-12-11 14:47:55 -08:00
  • a838421ea3 model: conversion and hyperparameter fixes for ministral and devstral (#13424) Jeffrey Morgan 2025-12-11 13:04:00 -08:00
  • 1c4e85b4df routes: add logprobs in tool calls (#13238) EasonLin 2025-12-11 09:28:41 +08:00
  • dac4f17fea cmd/bench: fix binary name in README (#13276) Eloi Torrents 2025-12-10 23:16:58 +01:00
  • 56b8fb024c cmd/bench: fix options table in cmd/bench/README.md (#13216) Julia Scheaffer 2025-12-10 16:07:48 -06:00
  • b95693056c feat: llama.cpp bump (17f7f4) for SSM performance improvements (#13408) Gabe Goodhart 2025-12-10 13:59:27 -07:00
  • c34fc64688 app/ui: use requestAnimationFrame to prevent bottom line cutoff in streaming thinking display (#13137) Eva H 2025-12-10 15:29:48 -05:00
  • 7cf6f18c1f app/ui: refactor to use Ollama endpoints for user auth and health checks (#13081) Eva H 2025-12-10 15:24:31 -05:00
  • bbbb6b2a01 app/ui: fix model capabilities not updating after download completion (#13179) Eva H 2025-12-10 14:40:02 -05:00
  • 76f88caf43 nomic-embed-text:v2: model implementation (#13162) nicole pardal 2025-12-09 14:24:51 -08:00
  • 2bccf8c624 renderers/parsers: olmo3 instruct (#13383) Parth Sareen 2025-12-09 11:12:27 -08:00
  • 0c5e5f6630 parsers/renderers: olmo3 think (#13290) Parth Sareen 2025-12-09 10:41:47 -08:00
  • d475d1f081 fix: qwen2.5vl metal argsort Michael Yang 2025-12-08 13:17:03 -08:00
  • d2f334c1f7 model: add rnj-1 inference support (#13354) Jeffrey Morgan 2025-12-08 16:49:17 -08:00
  • 603ceefaa6 refactor rope Michael Yang 2025-11-18 15:17:03 -08:00
  • e082d60a24 truncation: fixed runner truncation logic + removed server truncation (#12839) nicole pardal 2025-12-08 11:20:28 -08:00
  • 5dae738067 CI: use vendor base commit in cache keys (#13348) Daniel Hiltgen 2025-12-08 09:48:49 -08:00
  • 0c78723174 readme: fix broken Swollama link in community integrations (#13370) JJ 2025-12-07 21:49:52 -08:00
  • 5a41d69b2a fs/ggml: write int32 and int64 values to gguf files (#13335) Jeffrey Morgan 2025-12-07 21:49:14 -08:00
  • c146a138e3 ggml: handle all streams (#13350) Daniel Hiltgen 2025-12-05 16:10:33 -08:00
  • 31b8c6a214 fix(api): correct Content-Type header for /api/chat and /api/generate when using cloud models (#13279) Sos Pogosyan 2025-12-05 08:33:07 +03:00
  • 2dd3f3c67c Merge branch 'ollama:main' into main v0.13.2 likelovewant 2025-12-05 12:25:10 +08:00
  • 9191dfaf05 llm: Enable flash attention for mistral3 by default Jesse Gross 2025-12-04 12:16:52 -08:00
  • 1108d8b34e ggml: Enable flash attention for vision encoders Jesse Gross 2025-12-02 15:39:27 -08:00
  • 7837a5bc7e ggml: Always set cache padding to 256 Jesse Gross 2025-12-04 11:42:30 -08:00
  • 0a844f8e96 convert: add deepseek converter (#12980) Patrick Devine 2025-12-04 13:49:30 -08:00
  • a03223b86f cmd/bench: support writing benchmark output to file (#13263) Eloi Torrents 2025-12-04 22:22:41 +01:00
  • 0cf7794b16 ggml update to b7108 (#12992) Daniel Hiltgen 2025-12-03 19:43:29 -08:00
  • 854d40edc5 ci: restore previous linter rules (#13322) Jeffrey Morgan 2025-12-03 18:55:02 -08:00
  • 84a2cedf18 app: relay thinking false to server (#13319) Bruce MacDonald 2025-12-03 15:06:55 -08:00
  • 3f30836734 CUDA: filter devices on secondary discovery (#13317) Daniel Hiltgen 2025-12-03 12:58:16 -08:00
  • cc9555aff0 Update user message format for temperature query (#13256) Nathan Hook 2025-12-02 16:08:39 -07:00
  • 20aee96706 Add Vulkan GPU support instructions in development.md (#13265) hello_world 2025-12-03 05:37:32 +08:00
  • 18b5958d46 test: avoid ministral tools test on low vram (#13302) Daniel Hiltgen 2025-12-02 13:18:55 -08:00
  • 5317202c38 llm: Don't always evict models on CPU-only systems Jesse Gross 2025-11-25 14:51:02 -08:00
  • d771043e88 test: add ministral-3 (#13300) Daniel Hiltgen 2025-12-02 09:52:16 -08:00
  • f8f1071818 CUDA: verify CC is supported by target library (#13298) Daniel Hiltgen 2025-12-02 09:28:41 -08:00
  • d3e0a0dee4 model: ministral w/ llama4 scaling (#13292) Patrick Devine 2025-12-01 23:20:14 -08:00
  • 554172759c win: warn if ggml-base detected in PATH (#13289) Daniel Hiltgen 2025-12-01 15:36:47 -08:00
  • 5b6a8e6001 api/client: handle non-json streaming errors (#13007) Bruce MacDonald 2025-12-01 15:10:16 -08:00
  • 467bbc0dd5 jetpack: require exact match or skip cuda_jetpack* (#13288) Daniel Hiltgen 2025-12-01 12:48:16 -08:00
  • 6d9f9323c5 .gitattributes: add app/webview to linguist-vendored (#13274) Jeffrey Morgan 2025-11-29 23:46:10 -05:00
  • 0c2489605d docs: fix output formatting in faq.mdx (#13231) Ondrej Kokes 2025-11-29 01:19:21 +01:00
  • 8b1b89a984 docs: remove deprecated parameters (#13237) EntropyYue 2025-11-26 10:03:09 +08:00
  • 58a46a6e73 Merge branch 'ollama:main' into main v0.13.0 likelovewant 2025-11-22 17:42:25 +08:00
  • 47e272c35a app/cmd: update ollama help to navigate to ollama doc instead of github page (#13174) Eva H 2025-11-20 16:30:35 -05:00
  • 417a81fda3 app: open app instead of always navigating to / on connect (#13164) Jeffrey Morgan 2025-11-20 12:59:17 -08:00
  • dba62ff3a5 discovery: fix cuda overlap case (#13176) Daniel Hiltgen 2025-11-20 12:15:37 -08:00
  • d70e935526 Parser for Cogito v2 (#13145) Grace 2025-11-19 17:21:07 -08:00
  • 5c1063df7f deepseek2: upgrade to run v3+ models (#13166) Michael Yang 2025-11-19 17:05:39 -08:00
  • cb485b2019 kvcache: Run tests both with and without PermutedV Jesse Gross 2025-11-19 10:44:38 -08:00
  • b2af50960f nomic-embed: nomic-embed-text defaulted to ollama runner (#13144) nicole pardal 2025-11-19 13:03:44 -08:00
  • eac5b8bfbd chore: mark vulkan shaders as vendored files Michael Yang 2025-11-18 19:59:40 -08:00
  • 604e43b28d models: enable deepseek2 (deepseek v3.1 w/ MLA) on the new engine (#13151) Patrick Devine 2025-11-18 22:03:50 -08:00
  • 53985b3c4d kvcache: Use SetRows to store cache data Jesse Gross 2025-08-18 10:45:58 -07:00
  • b6e02cbbd2 ggml: Automatically make tensors contiguous on reshape Jesse Gross 2025-11-18 20:24:09 -08:00
  • 91935631ac Renderer for Cogito v2 (#13139) Grace 2025-11-18 19:06:34 -08:00
  • 8de30b568a nomic-embed-text model implementation (#13071) nicole pardal 2025-11-18 18:28:10 -08:00
  • 485da9fd35 win: exit instead of abort (#13138) Daniel Hiltgen 2025-11-18 16:33:33 -08:00
  • 0796d79d19 cuda: skip large batches Michael Yang 2025-11-18 11:13:37 -08:00
  • 92981ae3f2 deepseekocr Michael Yang 2025-10-31 19:15:32 -07:00
  • 8ed1adf3db docs: fix typo in vscode.mdx (#13116) Lhiam Andrei Lingco 2025-11-19 05:18:42 +08:00
  • 440a3823a6 fix(tokenizer): add special tokens to empty inputs (#13091) Michael Yang 2025-11-18 11:16:56 -08:00