Files
amd-strix-halo-vllm-toolboxes/benchmarks/benchmark_results/btbtyler09_Qwen3-Coder-30B-A3B-Instruct-gptq-8bit_cluster_tp2_eth_throughput.json
2026-02-23 19:39:19 +00:00

7 lines
190 B
JSON

{
"elapsed_time": 534.8865945799625,
"num_requests": 200,
"total_num_tokens": 146805,
"requests_per_second": 0.3739110346503573,
"tokens_per_second": 274.46004720922855
}