| Release list | ||
|---|---|---|
| 0.15.4 | RECENT | |
| 0.15.3 | RECENT | |
| 0.15.2 | ||
| 0.15.1 | ||
| 0.15.0 | ||
| 0.14.3 | ||
| 0.14.2 | ||
| 0.14.1 | ||
| 0.14.0 | ||
| 0.13.5 | ||
| 0.13.4 | ||
| 0.13.3 | ||
| 0.13.2 | ||
| 0.13.1 | ||
| 0.13.0 | ||
| 0.12.11 | ||
| 0.12.10 | ||
| 0.12.9 | ||
| 0.12.8 | ||
| 0.12.7 | ||
Ollama
- project on GitHub > ollama/ollama
- last check : with 0 version(s) added
notes:
Release notes:
What's Changed
- Flash attention is now enabled by default for vision models such as
mistral-3,gemma3,qwen3-vland more. This improves memory utilization and performance when providing images as input. - Fixed GPU detection on multi-GPU CUDA machines
- Fixed issue where
deepseek-v3.1would always think even with thinking is disabled in Ollama's app
New Contributors
- @chengcheng84 made their first contribution in https://github.com/ollama/ollama/pull/13265
- @nathan-hook made their first contribution in https://github.com/ollama/ollama/pull/13256
Full Changelog: https://github.com/ollama/ollama/compare/v0.13.1...v0.13.2-rc0