tr lamma AMD Ryzen Threadripper 7980X 64-Cores testing with a ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS) and AMD Radeon RX 7900 XT 20GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2401105-PTS-TRLAMMA345&grs .
tr lamma Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c d AMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads) ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS) AMD Device 14a4 128GB 2000GB Corsair MP700 PRO + 1000GB Western Digital WDS100T1X0E-00AFY0 AMD Radeon RX 7900 XT 20GB (2025/1249MHz) Realtek ALC1220 DELL U2723QE Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCI Ubuntu 23.10 6.7.0-060700rc2daily20231126-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 + Wayland 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.56) GCC 13.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
tr lamma llama-cpp: llama-2-7b.Q4_0.gguf llama-cpp: llama-2-13b.Q4_0.gguf llama-cpp: llama-2-70b-chat.Q5_0.gguf a b c d 31.29 18.24 3.46 30.79 18.32 3.47 31.21 18.18 3.48 32.55 18.54 3.51 OpenBenchmarking.org
Llama.cpp Model: llama-2-7b.Q4_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-7b.Q4_0.gguf a b c d 8 16 24 32 40 SE +/- 0.43, N = 3 SE +/- 0.15, N = 3 SE +/- 0.23, N = 15 31.29 30.79 31.21 32.55 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Llama.cpp Model: llama-2-13b.Q4_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-13b.Q4_0.gguf a b c d 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 18.24 18.32 18.18 18.54 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Llama.cpp Model: llama-2-70b-chat.Q5_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-70b-chat.Q5_0.gguf a b c d 0.7898 1.5796 2.3694 3.1592 3.949 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.46 3.47 3.48 3.51 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Phoronix Test Suite v10.8.5