granite-test-output.txt KVM testing on TencentOS Server 3.1 via the Phoronix Test Suite. AMD EPYC 9K84 96-Core - Cirrus Logic GD 5446 -: Processor: AMD EPYC 9K84 96-Core (16 Cores / 32 Threads), Motherboard: Tencent Cloud CVM v3.0 (seabios-1.9.1-qemu-project.org BIOS), Chipset: Intel 440FX 82441FX PMC, Memory: 8 x 16 GB RAM Smdbmds, Disk: 493GB, Graphics: Cirrus Logic GD 5446, Network: Red Hat Virtio device OS: TencentOS Server 3.1, Kernel: 5.4.119-19.0009.44 (x86_64), Compiler: GCC 8.5.0 20210514 + Clang 17.0.6, File-System: ext4, Screen Resolution: 1024x768, System Layer: KVM Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better