Skip to content

Implement '--keep-split' to quantize model into several shards #10947

Implement '--keep-split' to quantize model into several shards

Implement '--keep-split' to quantize model into several shards #10947

windows-latest-cmake (arm64, -A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_L...

succeeded Apr 23, 2024 in 5m 12s