Tests for a future article. AMD EPYC 7551 32-Core testing with a GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS) and ASPEED on Debian 12 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 2406025-NE-OLDEPYCAI16
old epyc ai Suite1.0.0SystemTest suite extracted from old epyc ai.pts/whisper-cpp-1.1.0-m models/ggml-base.en.bin -f ../2016-state-of-the-union.wavModel: ggml-base.en - Input: 2016 State of the Unionpts/whisper-cpp-1.1.0-m models/ggml-small.en.bin -f ../2016-state-of-the-union.wavModel: ggml-small.en - Input: 2016 State of the Unionpts/whisper-cpp-1.1.0-m models/ggml-medium.en.bin -f ../2016-state-of-the-union.wavModel: ggml-medium.en - Input: 2016 State of the Unionpts/llama-cpp-1.1.0-m ../Meta-Llama-3-8B-Instruct-Q8_0.ggufModel: Meta-Llama-3-8B-Instruct-Q8_0.ggufpts/llamafile-1.2.0run-llava --gpu DISABLETest: llava-v1.6-mistral-7b.Q8_0 - Acceleration: CPUpts/llamafile-1.2.0run-llama3 --gpu DISABLETest: Meta-Llama-3-8B-Instruct.F16 - Acceleration: CPUpts/llamafile-1.2.0run-tinyllama --gpu DISABLETest: TinyLlama-1.1B-Chat-v1.0.BF16 - Acceleration: CPUpts/llamafile-1.2.0run-mistral --gpu DISABLETest: mistral-7b-instruct-v0.2.Q5_K_M - Acceleration: CPUpts/llamafile-1.2.0run-wizardcoder --gpu DISABLETest: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU