Local Ai
b9414
b9414 is a release build of llama.cpp that includes improvements to CUDA PTX version checking , which helps prevent incorrect kernel dispatch on different GPU architectures. This build also adds suppo
b9414 is a release build of llama.cpp that includes improvements to CUDA PTX version checking , which helps prevent incorrect kernel dispatch on different GPU architectures. This build also adds support for the DeepSeek V3.2 model family with the DSA lightning indexer . The release represents incremental improvements to the llama.cpp inference engine, which enables efficient LLM inference in C/C++ across multiple hardware platforms.
Source: llama.cpp Releases | 2026-05-29