What's Changed (this repo branch)
- Sync to v0.13.0
What's Changed (from Ollama)
New Models
- DeepSeek-OCR: DeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing.
- Cogito-V2.1: instruction tuned generative models, currently the best open-weight LLM by a US company
What's Changed
- DeepSeek-OCR is now supported
- DeepSeek-V3.1 architecture is now supported in Ollama's engine
- Fixed performance issues that arose in Ollama 0.12.11 on CUDA
- Fixed issue where Linux install packages were missing required Vulkan libraries
- Improved CPU and memory detection while in containers/cgroups
- Improved VRAM information detection for AMD GPUs
- Improved KV cache performance to no longer require defragmentation
Contributors
- @lnicola made their first contribution in ollama#13096
- @vignesh1507 made their first contribution in ollama#13078
- @pierwill made their first contribution in ollama#12995
- @jjuliano made their first contribution in ollama#11877
- @omahs made their first contribution in ollama#10683
- @SiLeader made their first contribution in ollama#10292
- @ssam18 made their first contribution in ollama#13124
- @seolyam made their first contribution in ollama#13116
Full Changelog: v0.12.11...v0.13.0