TechIntel Xeon's claimed throughput gains in MLPerf Inference v6.1
Intel says its Xeon processors delivered 2.4x higher Llama 3.1 8B server throughput and 56% higher offline throughput compared with MLPerf Inference v6.0.
TLDR
Intel credits continued software and system-level optimizations for its Xeon processors' MLPerf Inference v6.1 results. The company reports 2.4x higher Llama 3.1 8B server throughput and 56% higher offline throughput compared with v6.0.
Intel Xeon's claimed throughput gains in MLPerf Inference v6.1
Intel says its Xeon processors delivered 2.4x higher Llama 3.1 8B server throughput and 56% higher offline throughput compared with MLPerf Inference v6.0.
TLDR
Intel credits continued software and system-level optimizations for its Xeon processors' MLPerf Inference v6.1 results. The company reports 2.4x higher Llama 3.1 8B server throughput and 56% higher offline throughput compared with v6.0.