v0.31.2
Breaking Changes📦 ollamaView on GitHub →
⚠ 2 breaking✨ 2 features🐛 3 fixes🔧 1 symbols
Summary
This release focuses on improving hardware compatibility, particularly for CUDA and ROCm, and cleans up experimental code paths. Key changes include enabling FA on older CUDA GPUs and removing deprecated environment flags.
⚠️ Breaking Changes
- The environment variable OLLAMA_EXPERIMENT=client2 has been removed, which might break workflows relying on this experimental feature.
- ROCm support for no longer supported devices has been removed.
Migration Steps
- Remove usage of the OLLAMA_EXPERIMENT=client2 environment variable if present in your setup.
✨ New Features
- Enabled FA (Flash Attention) support on CUDA Compute Capability 6.x GPUs.
- Introduced agent core harnessing capabilities.
🐛 Bug Fixes
- Fixed CUDA toolkit lookup and parallel execution issues.
- Resolved an issue where the JetPack runner absence prevented fallback to standard CUDA.
- Updated file opening to use UTF-8-safe encoding.