Releases: AuditAIH/llama.cpp_rerank
Releases · AuditAIH/llama.cpp_rerank
0.0.2_b7524_cuda13.0_ubuntu24.04_amd64_allcuda
0.0.1_b7524_cuda13.0_ubuntu24.04_amd64 For RTX5090(sm_120)
build on b7524_cuda13.0_ubuntu24.04_amd64
git clone -b b7524 --depth 1 https://github.com/ggml-org/llama.cpp