llama cpp update

AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon RX 6700 XT 12GB on Ubuntu 24.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2411230-PTS-LLAMACPP41&grt.

llama cpp updateProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionabcAMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads)System76 Thelio Major (FA Z5 BIOS)AMD Device 14a44 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA21000GB CT1000T700SSD5AMD Radeon RX 6700 XT 12GBAMD Device 14ccDELL P2415QAquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6EUbuntu 24.046.8.0-48-generic (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.0.9-0ubuntu0.2 (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 + reg_file_data_sampling: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

llama cpp updatellama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048abc15.54102.05123.08154.6816.46103.99126.34149.4776.34249.15328.55418.9615.50103.50124.40153.2116.52105.14129.31149.6576.53250.07329.89405.8215.60104.43122.97153.5116.45103.32126.69154.2676.56250.38341.69406.84OpenBenchmarking.org

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128abc48121620SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 315.5415.5015.601. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512abc20406080100SE +/- 1.42, N = 15SE +/- 1.15, N = 3SE +/- 1.20, N = 15102.05103.50104.431. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024abc306090120150SE +/- 0.81, N = 3SE +/- 0.96, N = 15SE +/- 0.46, N = 3123.08124.40122.971. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048abc306090120150SE +/- 1.85, N = 15SE +/- 1.13, N = 15SE +/- 1.32, N = 15154.68153.21153.511. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128abc48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 316.4616.5216.451. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512abc20406080100SE +/- 1.12, N = 15SE +/- 1.28, N = 3SE +/- 1.25, N = 13103.99105.14103.321. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024abc306090120150SE +/- 0.27, N = 3SE +/- 0.30, N = 3SE +/- 1.65, N = 3126.34129.31126.691. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048abc306090120150SE +/- 0.58, N = 3SE +/- 0.97, N = 3SE +/- 1.30, N = 15149.47149.65154.261. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128abc20406080100SE +/- 0.37, N = 3SE +/- 0.45, N = 3SE +/- 0.34, N = 376.3476.5376.561. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512abc50100150200250SE +/- 4.04, N = 12SE +/- 4.43, N = 12SE +/- 2.38, N = 3249.15250.07250.381. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024abc70140210280350SE +/- 3.24, N = 3SE +/- 2.46, N = 3SE +/- 2.74, N = 3328.55329.89341.691. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048abc90180270360450SE +/- 3.92, N = 3SE +/- 3.66, N = 3SE +/- 4.49, N = 15418.96405.82406.841. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas


Phoronix Test Suite v10.8.5