b8702
📦 llama-cppView on GitHub →
✨ 3 features🔧 1 symbols
Summary
This release significantly speeds up CUDA graph property checks using hashing and introduces optimizations like 'seen node' and 'memcp'. It also provides extensive pre-built binaries for diverse operating systems and hardware configurations.
✨ New Features
- CUDA graph property checks are now faster by computing a fast hash instead of an expensive property check.
- Introduced use of 'seen node' optimization in CUDA graphs.
- Introduced use of 'memcp' optimization in CUDA graphs.