Local Ai
b8740
llama.cpp release **b8740** (commit `e34f042`) is a build of the open-source C/C++ LLM inference engine focused on the change 'CUDA: fuse muls' (PR #21665), which optimizes CUDA performance by fusi...
llama.cpp release b8740 (commit e34f042) is a build of the open-source C/C++ LLM inference engine focused on the change "CUDA: fuse muls" (PR #21665), which optimizes CUDA performance by fusing multiply operations. The release ships pre-built binaries for a wide range of platforms including macOS (Apple Silicon and Intel), Linux (x64, arm64, s390x, Vulkan, ROCm, OpenVINO), Windows (CPU, CUDA 12/13, Vulkan, SYCL, HIP), and openEuler variants. Shortly after release, a known issue was reported where CUDA builds produce gibberish output, traced back to the fused-muls change introduced around this build.
Related
Source: local-ai