cturan/llama.cpp @ qwen3_next

spiegel van https://github.com/cturan/llama.cpp

cturan 2b40434af3 Enhance CUDA kernels for CUMSUM and DELTA_NET operations		2 maanden geleden
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	5 maanden geleden
include	7eef0bd948 Rewrite recurrent delta + softmax to separate ops	3 maanden geleden
src	2b40434af3 Enhance CUDA kernels for CUMSUM and DELTA_NET operations	2 maanden geleden
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 jaar geleden
CMakeLists.txt	43eb7a7757 Now that eval's running move delta net stuff back to llama-model, add cbs	3 maanden geleden