ggml-zendnn : add Q8_0 quantization support by z-sachin · Pull Request #23414 · ggml-org/llama.cpp
英文标题：ggml-zendnn : add Q8_0 quantization support by z-sachin · Pull Request #23414 · ggml-org/llama.cpp
Benchmark Results Benchmark configuration: threads = 96 type_k = bf16 type_v = bf16 Llama-3.1-8B-Instruct Q8_0 Prompt Size GGML_CPU_Q8_0 t/s ZenDNN_Q8_0 t/s Gain 256 472.28 730.87 54.75% 512 450.86 832.48 84.64% 768 446.81 864.52 93.49% 1024 439.58 800.15 82.03% 2048 405.07 778.
打开原文相关 2 · 机会 0
中文
Benchmark Results Benchmark configuration: threads = 96 type_k = bf16 type_v = bf16 Llama-3.1-8B-Instruct Q8_0 Prompt Size GGML_CPU_Q8_0 t/s ZenDNN_Q8_0 t/s Gain 256 472.28 730.87 54.75% 512 450.86 832.48 84.64% 768 446.81 864.52 93.49% 1024 439.58 800.15 82.03% 2048 405.07 778.
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Benchmark Results Benchmark configuration: threads = 96 type_k = bf16 type_v = bf16 Llama-3.1-8B-Instruct Q8_0 Prompt Size GGML_CPU_Q8_0 t/s ZenDNN_Q8_0 t/s Gain 256 472.28 730.87 54.75% 512 450.86 832.48 84.64% 768 446.81 864.52 93.49% 1024 439.58 800.15 82.03% 2048 405.07 778.