b9119
📦 llama-cppView on GitHub →
🐛 1 fixes
Summary
This release addresses a specific performance regression on Windows Vulkan workloads involving Intel GPUs and BF16 computations. A refactoring was implemented to conditionally use l_warptile.
Migration Steps
- Use l_warptile only when coopamt is available for BF16.
🐛 Bug Fixes
- Fixed a Windows performance regression for Vulkan BF16 workloads on Intel Xe2 and newer GPUs.