Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
8.98 |
4.37 |
227.44 |
5 |
15.31 |
5.1 |
971.34 |
25 |
21.08 |
6.02 |
4100.33 |
50 |
50.68 |
7.19 |
6745.78 |
100 |
209.66 |
8.62 |
10369.56 |
150 |
398.54 |
12.49 |
10383.16 |
200 |
501.44 |
17.76 |
9884.77 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
13.89 |
4.77 |
209.52 |
5 |
27.22 |
5.45 |
915.96 |
25 |
110.61 |
6.32 |
3924.39 |
50 |
112.02 |
8.3 |
5979.38 |
100 |
245.7 |
11.12 |
8878.96 |
150 |
5217.57 |
13.78 |
8955.7 |
200 |
9112.64 |
18.27 |
8443.89 |
250 |
21097.73 |
19.26 |
8256.58 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
19.97 |
4.77 |
208.88 |
5 |
57.87 |
5.45 |
908.9 |
25 |
170.91 |
6.57 |
3710.08 |
50 |
214.79 |
8.74 |
5582.41 |
100 |
373.73 |
12.41 |
7819.41 |
150 |
890.01 |
15.84 |
8935.06 |
200 |
3231.57 |
18.31 |
9151.55 |
250 |
6469.67 |
21.75 |
8725.87 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
82.87 |
6.04 |
161.51 |
5 |
249.06 |
7.04 |
664.39 |
25 |
372.59 |
11.61 |
2024.67 |
50 |
415.72 |
19.99 |
2398.11 |
100 |
501.51 |
33.71 |
2844.33 |
150 |
646.08 |
47.58 |
3047.56 |
200 |
6830.5 |
51.83 |
3008.29 |
250 |
14795.72 |
51.74 |
3030.76 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
443.88 |
11.3 |
86.79 |
5 |
1011.39 |
12.71 |
377.88 |
25 |
1432.91 |
21.41 |
1099.79 |
50 |
16505.76 |
32.16 |
1116.23 |
100 |
89292.14 |
32.21 |
1190.64 |
150 |
153371.08 |
32.17 |
1195.86 |
200 |
208680.03 |
32.14 |
1200.69 |
250 |
281213.01 |
32.19 |
1213.79 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
11.96 |
6.54 |
152.24 |
5 |
27.18 |
7.39 |
667.60 |
25 |
34.67 |
8.60 |
2858.90 |
50 |
56.65 |
10.04 |
4858.86 |
100 |
168.60 |
12.57 |
7478.74 |
150 |
479.48 |
14.66 |
8811.28 |
200 |
755.88 |
18.81 |
8864.97 |
250 |
957.59 |
24.77 |
8439.91 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
19.89 |
6.94 |
143.93 |
5 |
51.19 |
7.70 |
647.12 |
25 |
202.87 |
9.42 |
2625.41 |
50 |
329.35 |
11.62 |
4242.00 |
100 |
552.68 |
15.67 |
6268.04 |
150 |
782.65 |
20.32 |
7232.18 |
200 |
7996.68 |
21.76 |
7666.88 |
250 |
20815.08 |
21.96 |
7610.47 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
29.73 |
6.93 |
143.87 |
5 |
96.74 |
7.72 |
640.26 |
25 |
386.45 |
9.50 |
2530.05 |
50 |
625.88 |
12.03 |
3951.34 |
100 |
724.55 |
17.79 |
5326.15 |
150 |
1126.07 |
22.88 |
6241.50 |
200 |
1691.82 |
27.89 |
6548.23 |
250 |
5664.63 |
29.12 |
7150.32 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
128.32 |
8.14 |
119.30 |
5 |
503.39 |
8.88 |
506.79 |
25 |
1243.85 |
17.36 |
1259.32 |
50 |
1273.57 |
29.38 |
1561.19 |
100 |
6941.19 |
44.67 |
1689.99 |
150 |
21179.86 |
44.66 |
1690.45 |
200 |
35001.67 |
44.54 |
1694.93 |
250 |
49204.54 |
44.48 |
1703.87 |
Concurrency |
TTFT (ms) |
ITL (ms) |
Throughput(Tokens/s) |
---|---|---|---|
1 |
637.84 |
13.16 |
74.21 |
5 |
1881.45 |
13.50 |
346.33 |
25 |
19476.78 |
31.76 |
579.50 |
50 |
92969.97 |
31.81 |
558.51 |
100 |
216580.75 |
31.83 |
582.54 |
150 |
301171.32 |
31.79 |
583.14 |
200 |
348383.77 |
31.81 |
582.88 |
250 |
484376.95 |
31.85 |
584.58 |