cturan/llama.cpp

-ын хуулбар https://github.com/cturan/llama.cpp

Эзэн	SHA1 Мессеж	Огноо
compilade	9bc6db28d0 ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)	1 жил өмнө
R0CKSTAR	e54c35e4fb feat: Support Moore Threads GPU (#8383)	1 жил өмнө
Dibakar Gope	0f1a39f343 ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)	1 жил өмнө
Johannes Gäßler	cb5fad4c6c CUDA: refactor and optimize IQ MMVQ (#8215)	1 жил өмнө
Georgi Gerganov	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 жил өмнө