Files
amd-strix-halo-vllm-toolboxes/benchmarks/benchmark_results_rocm/Qwen_Qwen3-14B-AWQ_cluster_tp2_throughput.json
T

7 lines
190 B
JSON

{
"elapsed_time": 234.33056626700272,
"num_requests": 100,
"total_num_tokens": 75285,
"requests_per_second": 0.42674757114723666,
"tokens_per_second": 321.2769089381971
}