b9318
📦 llama-cppView on GitHub →
🐛 1 fixes🔧 1 symbols
Summary
This release includes a fix where the MTP layer kv-cache now correctly respects the draft type ctk. It also provides numerous pre-compiled binaries for various operating systems and hardware configurations.
🐛 Bug Fixes
- MTP layer kv-cache now respects draft type ctk.