Skip to content

llama : fix K-shift with quantized K and BLAS backend (#13113) #1266

llama : fix K-shift with quantized K and BLAS backend (#13113)

llama : fix K-shift with quantized K and BLAS backend (#13113) #1266

Annotations

2 warnings

windows-latest-cmake (noavx-x64, -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_A...

succeeded Apr 25, 2025 in 6m 18s