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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2411230-PTS-LLAMACPP41
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
November 23
  56 Minutes
b
November 23
  53 Minutes
c
November 24
  1 Hour, 15 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 1 Minute

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


llama cpp updateOpenBenchmarking.orgPhoronix Test SuiteAMD 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 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionLlama Cpp Update BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- 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

abcResult OverviewPhoronix Test Suite100%101%102%103%104%Llama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppCPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.1CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.2CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.2CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.1CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.5CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.5CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.1CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.2CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - T.G.1CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.5CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - T.G.1CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - T.G.1

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

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128cab48121620SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 315.6015.5415.501. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512cba20406080100SE +/- 1.20, N = 15SE +/- 1.15, N = 3SE +/- 1.42, N = 15104.43103.50102.051. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024bac306090120150SE +/- 0.96, N = 15SE +/- 0.81, N = 3SE +/- 0.46, N = 3124.40123.08122.971. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048acb306090120150SE +/- 1.85, N = 15SE +/- 1.32, N = 15SE +/- 1.13, N = 15154.68153.51153.211. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128bac48121620SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 316.5216.4616.451. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512bac20406080100SE +/- 1.28, N = 3SE +/- 1.12, N = 15SE +/- 1.25, N = 13105.14103.99103.321. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024bca306090120150SE +/- 0.30, N = 3SE +/- 1.65, N = 3SE +/- 0.27, N = 3129.31126.69126.341. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048cba306090120150SE +/- 1.30, N = 15SE +/- 0.97, N = 3SE +/- 0.58, N = 3154.26149.65149.471. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128cba20406080100SE +/- 0.34, N = 3SE +/- 0.45, N = 3SE +/- 0.37, N = 376.5676.5376.341. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512cba50100150200250SE +/- 2.38, N = 3SE +/- 4.43, N = 12SE +/- 4.04, N = 12250.38250.07249.151. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024cba70140210280350SE +/- 2.74, N = 3SE +/- 2.46, N = 3SE +/- 3.24, N = 3341.69329.89328.551. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048acb90180270360450SE +/- 3.92, N = 3SE +/- 4.49, N = 15SE +/- 3.66, N = 3418.96406.84405.821. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas