Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
25.05 |
13.21 |
75.36 |
5 |
64.82 |
12.64 |
387.55 |
25 |
146.11 |
15.31 |
1564.9 |
50 |
169.61 |
17.42 |
2743.6 |
100 |
235.17 |
23.28 |
4092.34 |
150 |
511.21 |
27.73 |
4962.78 |
200 |
582.07 |
31.22 |
5855.9 |
250 |
718.98 |
35.25 |
6429.95 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
38.64 |
14.24 |
70.14 |
5 |
109.06 |
13.68 |
364.24 |
25 |
393.58 |
15.86 |
1557.21 |
50 |
564.17 |
17.14 |
2868.22 |
100 |
640.42 |
22.64 |
4350.2 |
150 |
792.84 |
28.49 |
5183.08 |
200 |
1417.35 |
31.62 |
6168.81 |
250 |
2045.69 |
35.75 |
6511.88 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
59.89 |
14.24 |
69.98 |
5 |
180.35 |
13.72 |
360.12 |
25 |
571.16 |
16.38 |
1475.28 |
50 |
843.45 |
18.15 |
2631.13 |
100 |
740 |
25.55 |
3794.76 |
150 |
952.07 |
32.31 |
4493.57 |
200 |
980.89 |
37.92 |
5114.09 |
250 |
2632.73 |
41.92 |
5497.21 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
236.58 |
17.35 |
56.2 |
5 |
432.23 |
18.16 |
263.04 |
25 |
657.73 |
28.69 |
830.42 |
50 |
952.43 |
40.13 |
1169.61 |
100 |
1312.92 |
68.86 |
1378 |
150 |
1973.14 |
98.88 |
1428.94 |
200 |
2850.08 |
126.51 |
1455.09 |
250 |
11283.63 |
139.94 |
1488.41 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
1018.5 |
30.32 |
32.45 |
5 |
2116.84 |
31.29 |
153.71 |
25 |
3987.46 |
43.16 |
541.65 |
50 |
7012.87 |
56.95 |
793.95 |
100 |
93862.88 |
61.72 |
815.75 |
150 |
175864.67 |
61.73 |
815.38 |
200 |
240432.76 |
61.73 |
815.52 |
250 |
335844.98 |
61.75 |
828.23 |