Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
368.11 |
19.94 |
48.44 |
5 |
446.68 |
23.89 |
199.17 |
25 |
751.74 |
42.12 |
564.5 |
50 |
1083.13 |
63.72 |
738.78 |
100 |
17754.93 |
87.55 |
777.31 |
150 |
46381.93 |
87.39 |
777.94 |
200 |
73326.6 |
87.64 |
777.02 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
71.82 |
19.26 |
51.84 |
5 |
109.62 |
20.04 |
237.72 |
25 |
159.62 |
23.28 |
1032.56 |
50 |
232.46 |
25.58 |
1880.75 |
100 |
293.19 |
32.83 |
2914.64 |
150 |
448.16 |
45.57 |
3096.87 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
32.78 |
19.11 |
52.15 |
5 |
81.17 |
19.9 |
247.26 |
25 |
247.81 |
21.99 |
1080.83 |
50 |
377.42 |
23.94 |
1936.88 |
100 |
583.54 |
31.79 |
2886.57 |
150 |
831.88 |
44.81 |
3067.43 |
200 |
925.3 |
45.92 |
3947.82 |
250 |
1105.17 |
49.83 |
4521.68 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
103.2 |
19.31 |
51.54 |
5 |
125.56 |
20.52 |
234.76 |
25 |
195.68 |
24.76 |
979.58 |
50 |
243.19 |
28.55 |
1706.26 |
100 |
344.86 |
38.65 |
2507.94 |
150 |
568.88 |
54.06 |
2663.03 |
200 |
1384.9 |
58.11 |
3238.57 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
190.36 |
19.6 |
49.57 |
5 |
430.84 |
21.64 |
216.96 |
25 |
870.9 |
35 |
654.15 |
50 |
1066.1 |
51.56 |
903.17 |
100 |
1332.94 |
88.91 |
1062.3 |
150 |
3853.57 |
124.93 |
1070.78 |
200 |
17105.6 |
125.13 |
1064.79 |
250 |
30309.49 |
125.27 |
1073.5 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
1637.36 |
20.5 |
46.92 |
5 |
3126.01 |
27 |
175.65 |
25 |
33539.02 |
52.4 |
323.8 |
50 |
127678.39 |
51.08 |
335.75 |
100 |
277353.39 |
48.51 |
345.84 |
150 |
339462.09 |
48.51 |
342.77 |
200 |
336890.58 |
51.03 |
338.3 |
250 |
515613.11 |
49.4 |
349.04 |