ggml : reading the runtime sve config of the cpu (llama/8709) c26339f jdomke domke commited on Aug 3, 2024
Fix conversion of unnormalized BF16->BF16 weights (llama/7843) 8b10f59 Sigbjørn Skjæret compilade commited on Aug 2, 2024
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780) 9509586 Dibakar Gope commited on Jul 10, 2024
whisper : reorganize source code + improve CMake (#2256) f75c2e3 unverified ggerganov commited on Jun 26, 2024