llama.cpp version b9699 introduces support for MUL_MAT and OUT_PROD operations with Q1_0 precision via PR #24721. The release includes precompiled binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures and acceleration frameworks, including SYCL (FP32 and FP16), Vulkan, CUDA, ROCm, and OpenVINO.
llama.cpp Release b9699 Adds SYCL Support and Multiple Platform Binaries
Переведено с English → Русский