b10670
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release optimizes SYCL quantized KV decode for BMG hardware by routing it to TILE, while keeping VEC for other architectures until further validation.
✨ New Features
- Route quantized KV decode to TILE on Xe2 (BMG) for improved performance.