llmfit: starší verze ke stažení

1.1.10 (2026-08-17)
Features
- mcp: add RamaLama runtime discovery (#875) (b9d5f57)
- models: add the Qwen3.8 family and fix Qwen generation parsing (#893) (6e024b2)
Bug Fixes
- bench: align 7900 XT hardwareName with the existing slug entries (c25754a)
- expose MiniMax M3 vision capability (#793) (4801d4a)
- ollama: stop one sized install marking a whole model family installed (#863) (c9a5678)
- providers: resolve MLX community tags to catalog ids (#854) (#860) (b79f2df)
What's Changed
- bench(apple-m4-pro): 32 MLX results — first MLX entries, head-to-head vs llama.cpp Metal on identical hardware by @Akciali in #853
- [Automated] Weekly benchmark cache refresh by @github-actions[bot] in #851
- [Automated] Weekly model data refresh by @github-actions[bot] in #852
- chore(deps): bump rmcp from 1.8.0 to 2.2.0 by @dependabot[bot] in #845
- chore(deps): bump actions/setup-node from 6.4.0 to 7.0.0 by @dependabot[bot] in #846
- chore: replace deprecated serde_yml dependency by @luojiyin1987 in #859
- fix(ollama): stop one sized install marking a whole model family installed by @AlexsJones in #863
- fix: expose MiniMax M3 vision capability by @octo-patch in #793
- docs: update AGENTS.md architecture and testing guidance by @luojiyin1987 in #857
- bench: community results for intel-alder-lake-p-gt2-iris-xe-graphics-integrated by @datawookie in #868
- bench: community results for radeon-840m-860m-graphics by @thelooter in #855
- bench: Muse-Glimmer-30B on amd-radeon-rx-7900-xt and apple-m4-pro by @Akciali in #870
- fix(providers): resolve MLX community tags to catalog ids by @Akciali in #860
- bench: community results for nvidia-geforce-gtx-1070 by @kopop2000 in #871
- chore(deps): bump async-nats from 0.49.1 to 0.50.0 by @dependabot[bot] in #849
- feat(models): add the Qwen3.8 family and fix Qwen generation parsing by @AlexsJones in #893
- [Automated] Weekly model data refresh by @github-actions[bot] in #892
- chore(deps): bump serde_json from 1.0.150 to 1.0.151 by @dependabot[bot] in #889
- feat(mcp): add RamaLama runtime discovery by @luojiyin1987 in #875
- bench: Qwen3.8-27B on amd-radeon-rx-7900-xt by @Akciali in #884
- chore(main): release 1.1.10 by @AlexsJones in #864
New Contributors
- @thelooter made their first contribution in #855
- @kopop2000 made their first contribution in #871
Full Changelog: v1.1.9...v1.1.10