test,metric,tok_per_s pp512,prefill,1293.37 pp2048,prefill,1333.02 pp8192,prefill,1310.12 tg256,decode,32.46 tg1024,decode,32.03 pp2048+tg512,prefill,1323.95 pp2048+tg512,decode,31.92 pp8192+tg512,prefill,1297.68 pp8192+tg512,decode,31.43