cturan/llama.cpp @ e92734d51bcb82cc35f0a6b5a14928f0036b2c90

镜像来自 https://github.com/cturan/llama.cpp

Reese Levine 45363632cb ggml WebGPU: add support for quantization types (#15440)		5 月之前
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	5 月之前
include	92f7f0a53c ggml: add `conv3d` op (#15182)	5 月之前
src	45363632cb ggml WebGPU: add support for quantization types (#15440)	5 月之前
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 年之前
CMakeLists.txt	7a6e91ad26 CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)	5 月之前