Upload 3 files
Browse files
Dockerfile
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM python:3-bookworm
|
2 |
+
RUN apt-get update && apt-get install -y \
|
3 |
+
git \
|
4 |
+
&& rm -rf /var/lib/apt/lists/*
|
5 |
+
RUN curl -sSL https://install.python-poetry.org | python3 -
|
6 |
+
ENV PATH="/root/.local/bin:$PATH"
|
7 |
+
WORKDIR /app
|
8 |
+
RUN git clone https://github.com/huggingface/inference-benchmarker.git \
|
9 |
+
&& cd inference-benchmarker \
|
10 |
+
&& poetry install --no-root
|
11 |
+
COPY results results
|
12 |
+
WORKDIR /app/inference-benchmarker
|
13 |
+
CMD ["poetry", "run", "python", "extra/dashboard/app.py", "--from-results-dir", "/app/results"]
|
results/meta-llama_Llama-3_1-8B-Instruct_2025-04-02-07-50-23.json
ADDED
@@ -0,0 +1,951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"max_vus": 128,
|
4 |
+
"duration_secs": 120,
|
5 |
+
"benchmark_kind": "Rate",
|
6 |
+
"warmup_duration_secs": 30,
|
7 |
+
"rates": [
|
8 |
+
0.8,
|
9 |
+
2.4,
|
10 |
+
4.0,
|
11 |
+
5.6,
|
12 |
+
7.2,
|
13 |
+
8.8,
|
14 |
+
10.4,
|
15 |
+
12.0,
|
16 |
+
13.6,
|
17 |
+
15.2,
|
18 |
+
16.8,
|
19 |
+
18.4,
|
20 |
+
20.0,
|
21 |
+
21.6,
|
22 |
+
23.2,
|
23 |
+
24.0
|
24 |
+
],
|
25 |
+
"num_rates": 10,
|
26 |
+
"prompt_options": null,
|
27 |
+
"decode_options": {
|
28 |
+
"num_tokens": 200,
|
29 |
+
"min_tokens": 200,
|
30 |
+
"max_tokens": 200,
|
31 |
+
"variance": 100
|
32 |
+
},
|
33 |
+
"tokenizer": "meta-llama/Llama-3.1-8B-Instruct",
|
34 |
+
"model_name": "meta-llama/Llama-3.1-8B-Instruct",
|
35 |
+
"profile": null,
|
36 |
+
"meta": {
|
37 |
+
"version": "4d28897b4e345f4dfdd93d3434e50ac8afcdf9e1",
|
38 |
+
"engine": "TGI",
|
39 |
+
"tp": "1"
|
40 |
+
},
|
41 |
+
"run_id": "TGI-3.2.1"
|
42 |
+
},
|
43 |
+
"results": [
|
44 |
+
{
|
45 |
+
"id": "warmup",
|
46 |
+
"executor_type": "ConstantVUs",
|
47 |
+
"config": {
|
48 |
+
"max_vus": 1,
|
49 |
+
"duration_secs": 30,
|
50 |
+
"rate": null
|
51 |
+
},
|
52 |
+
"total_requests": 22,
|
53 |
+
"total_tokens": 3726,
|
54 |
+
"token_throughput_secs": 121.61045252166194,
|
55 |
+
"duration_ms": 30638,
|
56 |
+
"time_to_first_token_ms": {
|
57 |
+
"p50": 46.607,
|
58 |
+
"p60": 46.786,
|
59 |
+
"p70": 46.957,
|
60 |
+
"p80": 47.13,
|
61 |
+
"p90": 48.231,
|
62 |
+
"p95": 78.293,
|
63 |
+
"p99": 80.85,
|
64 |
+
"avg": 48.554
|
65 |
+
},
|
66 |
+
"inter_token_latency_ms": {
|
67 |
+
"p50": 7.973,
|
68 |
+
"p60": 7.982,
|
69 |
+
"p70": 7.99,
|
70 |
+
"p80": 8.0,
|
71 |
+
"p90": 8.043,
|
72 |
+
"p95": 8.083,
|
73 |
+
"p99": 8.125,
|
74 |
+
"avg": 7.927
|
75 |
+
},
|
76 |
+
"failed_requests": 0,
|
77 |
+
"successful_requests": 22,
|
78 |
+
"request_rate": 0.7180434663114769,
|
79 |
+
"total_tokens_sent": 1613,
|
80 |
+
"e2e_latency_ms": {
|
81 |
+
"p50": 1632.456,
|
82 |
+
"p60": 1633.79,
|
83 |
+
"p70": 1636.485,
|
84 |
+
"p80": 1638.246,
|
85 |
+
"p90": 1647.577,
|
86 |
+
"p95": 1688.143,
|
87 |
+
"p99": 1697.2,
|
88 |
+
"avg": 1392.459
|
89 |
+
}
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"id": "[email protected]/s",
|
93 |
+
"executor_type": "ConstantArrivalRate",
|
94 |
+
"config": {
|
95 |
+
"max_vus": 128,
|
96 |
+
"duration_secs": 120,
|
97 |
+
"rate": 0.8
|
98 |
+
},
|
99 |
+
"total_requests": 94,
|
100 |
+
"total_tokens": 14823,
|
101 |
+
"token_throughput_secs": 125.70685354915,
|
102 |
+
"duration_ms": 117917,
|
103 |
+
"time_to_first_token_ms": {
|
104 |
+
"p50": 26.689,
|
105 |
+
"p60": 28.276,
|
106 |
+
"p70": 29.925,
|
107 |
+
"p80": 31.171,
|
108 |
+
"p90": 31.927,
|
109 |
+
"p95": 32.252,
|
110 |
+
"p99": 33.737,
|
111 |
+
"avg": 27.559
|
112 |
+
},
|
113 |
+
"inter_token_latency_ms": {
|
114 |
+
"p50": 8.297,
|
115 |
+
"p60": 8.308,
|
116 |
+
"p70": 8.327,
|
117 |
+
"p80": 8.348,
|
118 |
+
"p90": 8.372,
|
119 |
+
"p95": 8.387,
|
120 |
+
"p99": 8.48,
|
121 |
+
"avg": 8.274
|
122 |
+
},
|
123 |
+
"failed_requests": 0,
|
124 |
+
"successful_requests": 94,
|
125 |
+
"request_rate": 0.7971695495932065,
|
126 |
+
"total_tokens_sent": 13915,
|
127 |
+
"e2e_latency_ms": {
|
128 |
+
"p50": 1675.47,
|
129 |
+
"p60": 1680.097,
|
130 |
+
"p70": 1683.628,
|
131 |
+
"p80": 1686.037,
|
132 |
+
"p90": 1689.112,
|
133 |
+
"p95": 1692.598,
|
134 |
+
"p99": 1711.849,
|
135 |
+
"avg": 1329.915
|
136 |
+
}
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"id": "[email protected]/s",
|
140 |
+
"executor_type": "ConstantArrivalRate",
|
141 |
+
"config": {
|
142 |
+
"max_vus": 128,
|
143 |
+
"duration_secs": 120,
|
144 |
+
"rate": 2.4
|
145 |
+
},
|
146 |
+
"total_requests": 283,
|
147 |
+
"total_tokens": 49472,
|
148 |
+
"token_throughput_secs": 417.57128544344323,
|
149 |
+
"duration_ms": 118475,
|
150 |
+
"time_to_first_token_ms": {
|
151 |
+
"p50": 29.056,
|
152 |
+
"p60": 29.943,
|
153 |
+
"p70": 30.586,
|
154 |
+
"p80": 31.684,
|
155 |
+
"p90": 32.58,
|
156 |
+
"p95": 33.297,
|
157 |
+
"p99": 42.848,
|
158 |
+
"avg": 29.12
|
159 |
+
},
|
160 |
+
"inter_token_latency_ms": {
|
161 |
+
"p50": 8.925,
|
162 |
+
"p60": 8.931,
|
163 |
+
"p70": 8.939,
|
164 |
+
"p80": 8.947,
|
165 |
+
"p90": 8.954,
|
166 |
+
"p95": 8.965,
|
167 |
+
"p99": 8.982,
|
168 |
+
"avg": 8.669
|
169 |
+
},
|
170 |
+
"failed_requests": 0,
|
171 |
+
"successful_requests": 283,
|
172 |
+
"request_rate": 2.3886779143858026,
|
173 |
+
"total_tokens_sent": 44403,
|
174 |
+
"e2e_latency_ms": {
|
175 |
+
"p50": 1804.541,
|
176 |
+
"p60": 1805.909,
|
177 |
+
"p70": 1807.748,
|
178 |
+
"p80": 1809.553,
|
179 |
+
"p90": 1812.308,
|
180 |
+
"p95": 1814.507,
|
181 |
+
"p99": 1817.862,
|
182 |
+
"avg": 1579.6
|
183 |
+
}
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"id": "[email protected]/s",
|
187 |
+
"executor_type": "ConstantArrivalRate",
|
188 |
+
"config": {
|
189 |
+
"max_vus": 128,
|
190 |
+
"duration_secs": 120,
|
191 |
+
"rate": 4.0
|
192 |
+
},
|
193 |
+
"total_requests": 474,
|
194 |
+
"total_tokens": 85697,
|
195 |
+
"token_throughput_secs": 720.8187174458998,
|
196 |
+
"duration_ms": 118888,
|
197 |
+
"time_to_first_token_ms": {
|
198 |
+
"p50": 28.261,
|
199 |
+
"p60": 29.236,
|
200 |
+
"p70": 30.047,
|
201 |
+
"p80": 31.071,
|
202 |
+
"p90": 32.258,
|
203 |
+
"p95": 32.956,
|
204 |
+
"p99": 44.447,
|
205 |
+
"avg": 28.686
|
206 |
+
},
|
207 |
+
"inter_token_latency_ms": {
|
208 |
+
"p50": 9.365,
|
209 |
+
"p60": 9.383,
|
210 |
+
"p70": 9.396,
|
211 |
+
"p80": 9.415,
|
212 |
+
"p90": 9.433,
|
213 |
+
"p95": 9.446,
|
214 |
+
"p99": 9.457,
|
215 |
+
"avg": 9.313
|
216 |
+
},
|
217 |
+
"failed_requests": 0,
|
218 |
+
"successful_requests": 474,
|
219 |
+
"request_rate": 3.9869315386694577,
|
220 |
+
"total_tokens_sent": 56591,
|
221 |
+
"e2e_latency_ms": {
|
222 |
+
"p50": 1890.864,
|
223 |
+
"p60": 1894.873,
|
224 |
+
"p70": 1898.381,
|
225 |
+
"p80": 1902.406,
|
226 |
+
"p90": 1906.151,
|
227 |
+
"p95": 1909.095,
|
228 |
+
"p99": 1912.544,
|
229 |
+
"avg": 1712.674
|
230 |
+
}
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"id": "[email protected]/s",
|
234 |
+
"executor_type": "ConstantArrivalRate",
|
235 |
+
"config": {
|
236 |
+
"max_vus": 128,
|
237 |
+
"duration_secs": 120,
|
238 |
+
"rate": 5.6
|
239 |
+
},
|
240 |
+
"total_requests": 660,
|
241 |
+
"total_tokens": 115159,
|
242 |
+
"token_throughput_secs": 966.2563530237055,
|
243 |
+
"duration_ms": 119180,
|
244 |
+
"time_to_first_token_ms": {
|
245 |
+
"p50": 29.312,
|
246 |
+
"p60": 30.64,
|
247 |
+
"p70": 31.75,
|
248 |
+
"p80": 32.952,
|
249 |
+
"p90": 44.096,
|
250 |
+
"p95": 46.404,
|
251 |
+
"p99": 48.15,
|
252 |
+
"avg": 30.915
|
253 |
+
},
|
254 |
+
"inter_token_latency_ms": {
|
255 |
+
"p50": 9.98,
|
256 |
+
"p60": 9.996,
|
257 |
+
"p70": 10.004,
|
258 |
+
"p80": 10.013,
|
259 |
+
"p90": 10.022,
|
260 |
+
"p95": 10.028,
|
261 |
+
"p99": 10.062,
|
262 |
+
"avg": 9.803
|
263 |
+
},
|
264 |
+
"failed_requests": 0,
|
265 |
+
"successful_requests": 660,
|
266 |
+
"request_rate": 5.537814612801827,
|
267 |
+
"total_tokens_sent": 113449,
|
268 |
+
"e2e_latency_ms": {
|
269 |
+
"p50": 2013.741,
|
270 |
+
"p60": 2017.376,
|
271 |
+
"p70": 2019.935,
|
272 |
+
"p80": 2021.638,
|
273 |
+
"p90": 2024.968,
|
274 |
+
"p95": 2026.227,
|
275 |
+
"p99": 2032.895,
|
276 |
+
"avg": 1754.082
|
277 |
+
}
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"id": "[email protected]/s",
|
281 |
+
"executor_type": "ConstantArrivalRate",
|
282 |
+
"config": {
|
283 |
+
"max_vus": 128,
|
284 |
+
"duration_secs": 120,
|
285 |
+
"rate": 7.2
|
286 |
+
},
|
287 |
+
"total_requests": 849,
|
288 |
+
"total_tokens": 151779,
|
289 |
+
"token_throughput_secs": 1267.369912316427,
|
290 |
+
"duration_ms": 119759,
|
291 |
+
"time_to_first_token_ms": {
|
292 |
+
"p50": 30.493,
|
293 |
+
"p60": 31.719,
|
294 |
+
"p70": 33.123,
|
295 |
+
"p80": 36.078,
|
296 |
+
"p90": 46.155,
|
297 |
+
"p95": 46.769,
|
298 |
+
"p99": 48.162,
|
299 |
+
"avg": 32.604
|
300 |
+
},
|
301 |
+
"inter_token_latency_ms": {
|
302 |
+
"p50": 10.423,
|
303 |
+
"p60": 10.475,
|
304 |
+
"p70": 10.5,
|
305 |
+
"p80": 10.524,
|
306 |
+
"p90": 10.555,
|
307 |
+
"p95": 10.575,
|
308 |
+
"p99": 10.597,
|
309 |
+
"avg": 10.321
|
310 |
+
},
|
311 |
+
"failed_requests": 0,
|
312 |
+
"successful_requests": 849,
|
313 |
+
"request_rate": 7.089235372196724,
|
314 |
+
"total_tokens_sent": 145128,
|
315 |
+
"e2e_latency_ms": {
|
316 |
+
"p50": 2100.596,
|
317 |
+
"p60": 2114.214,
|
318 |
+
"p70": 2119.354,
|
319 |
+
"p80": 2124.055,
|
320 |
+
"p90": 2130.161,
|
321 |
+
"p95": 2134.421,
|
322 |
+
"p99": 2140.161,
|
323 |
+
"avg": 1884.625
|
324 |
+
}
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"id": "[email protected]/s",
|
328 |
+
"executor_type": "ConstantArrivalRate",
|
329 |
+
"config": {
|
330 |
+
"max_vus": 128,
|
331 |
+
"duration_secs": 120,
|
332 |
+
"rate": 8.8
|
333 |
+
},
|
334 |
+
"total_requests": 1041,
|
335 |
+
"total_tokens": 181439,
|
336 |
+
"token_throughput_secs": 1528.9336762174746,
|
337 |
+
"duration_ms": 118670,
|
338 |
+
"time_to_first_token_ms": {
|
339 |
+
"p50": 33.409,
|
340 |
+
"p60": 41.426,
|
341 |
+
"p70": 45.116,
|
342 |
+
"p80": 45.65,
|
343 |
+
"p90": 47.216,
|
344 |
+
"p95": 47.524,
|
345 |
+
"p99": 47.814,
|
346 |
+
"avg": 36.264
|
347 |
+
},
|
348 |
+
"inter_token_latency_ms": {
|
349 |
+
"p50": 11.019,
|
350 |
+
"p60": 11.044,
|
351 |
+
"p70": 11.072,
|
352 |
+
"p80": 11.102,
|
353 |
+
"p90": 11.136,
|
354 |
+
"p95": 11.159,
|
355 |
+
"p99": 11.222,
|
356 |
+
"avg": 10.862
|
357 |
+
},
|
358 |
+
"failed_requests": 0,
|
359 |
+
"successful_requests": 1041,
|
360 |
+
"request_rate": 8.77220419503189,
|
361 |
+
"total_tokens_sent": 191937,
|
362 |
+
"e2e_latency_ms": {
|
363 |
+
"p50": 2223.571,
|
364 |
+
"p60": 2232.271,
|
365 |
+
"p70": 2241.046,
|
366 |
+
"p80": 2246.104,
|
367 |
+
"p90": 2253.422,
|
368 |
+
"p95": 2259.594,
|
369 |
+
"p99": 2267.867,
|
370 |
+
"avg": 1944.18
|
371 |
+
}
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"id": "[email protected]/s",
|
375 |
+
"executor_type": "ConstantArrivalRate",
|
376 |
+
"config": {
|
377 |
+
"max_vus": 128,
|
378 |
+
"duration_secs": 120,
|
379 |
+
"rate": 10.4
|
380 |
+
},
|
381 |
+
"total_requests": 1225,
|
382 |
+
"total_tokens": 208853,
|
383 |
+
"token_throughput_secs": 1750.44303623107,
|
384 |
+
"duration_ms": 119314,
|
385 |
+
"time_to_first_token_ms": {
|
386 |
+
"p50": 34.056,
|
387 |
+
"p60": 40.904,
|
388 |
+
"p70": 44.889,
|
389 |
+
"p80": 45.567,
|
390 |
+
"p90": 47.156,
|
391 |
+
"p95": 47.537,
|
392 |
+
"p99": 47.805,
|
393 |
+
"avg": 36.461
|
394 |
+
},
|
395 |
+
"inter_token_latency_ms": {
|
396 |
+
"p50": 11.655,
|
397 |
+
"p60": 11.693,
|
398 |
+
"p70": 11.73,
|
399 |
+
"p80": 11.772,
|
400 |
+
"p90": 11.827,
|
401 |
+
"p95": 11.861,
|
402 |
+
"p99": 11.909,
|
403 |
+
"avg": 11.475
|
404 |
+
},
|
405 |
+
"failed_requests": 0,
|
406 |
+
"successful_requests": 1225,
|
407 |
+
"request_rate": 10.266995060559632,
|
408 |
+
"total_tokens_sent": 219623,
|
409 |
+
"e2e_latency_ms": {
|
410 |
+
"p50": 2351.289,
|
411 |
+
"p60": 2360.059,
|
412 |
+
"p70": 2368.244,
|
413 |
+
"p80": 2378.908,
|
414 |
+
"p90": 2388.768,
|
415 |
+
"p95": 2395.775,
|
416 |
+
"p99": 2405.872,
|
417 |
+
"avg": 2012.23
|
418 |
+
}
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"id": "[email protected]/s",
|
422 |
+
"executor_type": "ConstantArrivalRate",
|
423 |
+
"config": {
|
424 |
+
"max_vus": 128,
|
425 |
+
"duration_secs": 120,
|
426 |
+
"rate": 12.0
|
427 |
+
},
|
428 |
+
"total_requests": 1411,
|
429 |
+
"total_tokens": 255188,
|
430 |
+
"token_throughput_secs": 2159.7525641398156,
|
431 |
+
"duration_ms": 118156,
|
432 |
+
"time_to_first_token_ms": {
|
433 |
+
"p50": 40.727,
|
434 |
+
"p60": 44.09,
|
435 |
+
"p70": 44.798,
|
436 |
+
"p80": 46.295,
|
437 |
+
"p90": 46.858,
|
438 |
+
"p95": 48.094,
|
439 |
+
"p99": 48.34,
|
440 |
+
"avg": 38.454
|
441 |
+
},
|
442 |
+
"inter_token_latency_ms": {
|
443 |
+
"p50": 12.566,
|
444 |
+
"p60": 12.629,
|
445 |
+
"p70": 12.67,
|
446 |
+
"p80": 12.718,
|
447 |
+
"p90": 12.802,
|
448 |
+
"p95": 12.951,
|
449 |
+
"p99": 13.08,
|
450 |
+
"avg": 12.404
|
451 |
+
},
|
452 |
+
"failed_requests": 0,
|
453 |
+
"successful_requests": 1411,
|
454 |
+
"request_rate": 11.941826684645358,
|
455 |
+
"total_tokens_sent": 272561,
|
456 |
+
"e2e_latency_ms": {
|
457 |
+
"p50": 2532.282,
|
458 |
+
"p60": 2547.776,
|
459 |
+
"p70": 2560.142,
|
460 |
+
"p80": 2570.947,
|
461 |
+
"p90": 2585.7,
|
462 |
+
"p95": 2612.572,
|
463 |
+
"p99": 2635.79,
|
464 |
+
"avg": 2297.575
|
465 |
+
}
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"id": "[email protected]/s",
|
469 |
+
"executor_type": "ConstantArrivalRate",
|
470 |
+
"config": {
|
471 |
+
"max_vus": 128,
|
472 |
+
"duration_secs": 120,
|
473 |
+
"rate": 13.6
|
474 |
+
},
|
475 |
+
"total_requests": 1564,
|
476 |
+
"total_tokens": 272803,
|
477 |
+
"token_throughput_secs": 2293.5215462094866,
|
478 |
+
"duration_ms": 118945,
|
479 |
+
"time_to_first_token_ms": {
|
480 |
+
"p50": 44.852,
|
481 |
+
"p60": 46.319,
|
482 |
+
"p70": 46.872,
|
483 |
+
"p80": 48.169,
|
484 |
+
"p90": 49.674,
|
485 |
+
"p95": 51.154,
|
486 |
+
"p99": 53.485,
|
487 |
+
"avg": 42.864
|
488 |
+
},
|
489 |
+
"inter_token_latency_ms": {
|
490 |
+
"p50": 25.88,
|
491 |
+
"p60": 26.011,
|
492 |
+
"p70": 26.149,
|
493 |
+
"p80": 26.243,
|
494 |
+
"p90": 26.308,
|
495 |
+
"p95": 26.354,
|
496 |
+
"p99": 26.436,
|
497 |
+
"avg": 24.547
|
498 |
+
},
|
499 |
+
"failed_requests": 0,
|
500 |
+
"successful_requests": 1564,
|
501 |
+
"request_rate": 13.148930540615892,
|
502 |
+
"total_tokens_sent": 255933,
|
503 |
+
"e2e_latency_ms": {
|
504 |
+
"p50": 5177.262,
|
505 |
+
"p60": 5201.64,
|
506 |
+
"p70": 5238.214,
|
507 |
+
"p80": 5261.34,
|
508 |
+
"p90": 5275.17,
|
509 |
+
"p95": 5286.208,
|
510 |
+
"p99": 5302.579,
|
511 |
+
"avg": 4359.271
|
512 |
+
}
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"id": "[email protected]/s",
|
516 |
+
"executor_type": "ConstantArrivalRate",
|
517 |
+
"config": {
|
518 |
+
"max_vus": 128,
|
519 |
+
"duration_secs": 120,
|
520 |
+
"rate": 15.2
|
521 |
+
},
|
522 |
+
"total_requests": 1759,
|
523 |
+
"total_tokens": 309348,
|
524 |
+
"token_throughput_secs": 2580.5086165701296,
|
525 |
+
"duration_ms": 119878,
|
526 |
+
"time_to_first_token_ms": {
|
527 |
+
"p50": 45.707,
|
528 |
+
"p60": 47.05,
|
529 |
+
"p70": 47.656,
|
530 |
+
"p80": 48.721,
|
531 |
+
"p90": 51.476,
|
532 |
+
"p95": 53.138,
|
533 |
+
"p99": 55.565,
|
534 |
+
"avg": 44.101
|
535 |
+
},
|
536 |
+
"inter_token_latency_ms": {
|
537 |
+
"p50": 26.733,
|
538 |
+
"p60": 26.968,
|
539 |
+
"p70": 27.102,
|
540 |
+
"p80": 27.19,
|
541 |
+
"p90": 27.265,
|
542 |
+
"p95": 27.368,
|
543 |
+
"p99": 27.441,
|
544 |
+
"avg": 26.359
|
545 |
+
},
|
546 |
+
"failed_requests": 0,
|
547 |
+
"successful_requests": 1759,
|
548 |
+
"request_rate": 14.673166325778274,
|
549 |
+
"total_tokens_sent": 270134,
|
550 |
+
"e2e_latency_ms": {
|
551 |
+
"p50": 5326.968,
|
552 |
+
"p60": 5382.346,
|
553 |
+
"p70": 5428.823,
|
554 |
+
"p80": 5452.294,
|
555 |
+
"p90": 5469.218,
|
556 |
+
"p95": 5483.97,
|
557 |
+
"p99": 5502.975,
|
558 |
+
"avg": 4685.437
|
559 |
+
}
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"id": "[email protected]/s",
|
563 |
+
"executor_type": "ConstantArrivalRate",
|
564 |
+
"config": {
|
565 |
+
"max_vus": 128,
|
566 |
+
"duration_secs": 120,
|
567 |
+
"rate": 16.8
|
568 |
+
},
|
569 |
+
"total_requests": 1928,
|
570 |
+
"total_tokens": 330549,
|
571 |
+
"token_throughput_secs": 2759.3148813615194,
|
572 |
+
"duration_ms": 119793,
|
573 |
+
"time_to_first_token_ms": {
|
574 |
+
"p50": 46.472,
|
575 |
+
"p60": 46.857,
|
576 |
+
"p70": 48.168,
|
577 |
+
"p80": 50.368,
|
578 |
+
"p90": 53.407,
|
579 |
+
"p95": 55.802,
|
580 |
+
"p99": 72.801,
|
581 |
+
"avg": 45.931
|
582 |
+
},
|
583 |
+
"inter_token_latency_ms": {
|
584 |
+
"p50": 27.881,
|
585 |
+
"p60": 28.021,
|
586 |
+
"p70": 28.093,
|
587 |
+
"p80": 28.16,
|
588 |
+
"p90": 28.336,
|
589 |
+
"p95": 28.602,
|
590 |
+
"p99": 29.638,
|
591 |
+
"avg": 27.078
|
592 |
+
},
|
593 |
+
"failed_requests": 0,
|
594 |
+
"successful_requests": 1928,
|
595 |
+
"request_rate": 16.094313070876055,
|
596 |
+
"total_tokens_sent": 320581,
|
597 |
+
"e2e_latency_ms": {
|
598 |
+
"p50": 5553.009,
|
599 |
+
"p60": 5600.423,
|
600 |
+
"p70": 5629.869,
|
601 |
+
"p80": 5644.616,
|
602 |
+
"p90": 5671.609,
|
603 |
+
"p95": 5710.139,
|
604 |
+
"p99": 5944.138,
|
605 |
+
"avg": 4721.266
|
606 |
+
}
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"id": "[email protected]/s",
|
610 |
+
"executor_type": "ConstantArrivalRate",
|
611 |
+
"config": {
|
612 |
+
"max_vus": 128,
|
613 |
+
"duration_secs": 120,
|
614 |
+
"rate": 18.4
|
615 |
+
},
|
616 |
+
"total_requests": 2118,
|
617 |
+
"total_tokens": 357373,
|
618 |
+
"token_throughput_secs": 2982.4464814578682,
|
619 |
+
"duration_ms": 119825,
|
620 |
+
"time_to_first_token_ms": {
|
621 |
+
"p50": 59.209,
|
622 |
+
"p60": 64.399,
|
623 |
+
"p70": 69.696,
|
624 |
+
"p80": 75.067,
|
625 |
+
"p90": 80.705,
|
626 |
+
"p95": 84.049,
|
627 |
+
"p99": 88.502,
|
628 |
+
"avg": 59.862
|
629 |
+
},
|
630 |
+
"inter_token_latency_ms": {
|
631 |
+
"p50": 28.563,
|
632 |
+
"p60": 28.749,
|
633 |
+
"p70": 28.916,
|
634 |
+
"p80": 29.057,
|
635 |
+
"p90": 29.191,
|
636 |
+
"p95": 29.317,
|
637 |
+
"p99": 30.202,
|
638 |
+
"avg": 28.34
|
639 |
+
},
|
640 |
+
"failed_requests": 0,
|
641 |
+
"successful_requests": 2118,
|
642 |
+
"request_rate": 17.67571038586509,
|
643 |
+
"total_tokens_sent": 398184,
|
644 |
+
"e2e_latency_ms": {
|
645 |
+
"p50": 5708.277,
|
646 |
+
"p60": 5743.555,
|
647 |
+
"p70": 5787.666,
|
648 |
+
"p80": 5828.147,
|
649 |
+
"p90": 5862.892,
|
650 |
+
"p95": 5894.271,
|
651 |
+
"p99": 6066.881,
|
652 |
+
"avg": 4844.433
|
653 |
+
}
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"id": "[email protected]/s",
|
657 |
+
"executor_type": "ConstantArrivalRate",
|
658 |
+
"config": {
|
659 |
+
"max_vus": 128,
|
660 |
+
"duration_secs": 120,
|
661 |
+
"rate": 20.0
|
662 |
+
},
|
663 |
+
"total_requests": 2290,
|
664 |
+
"total_tokens": 386940,
|
665 |
+
"token_throughput_secs": 3227.511698507537,
|
666 |
+
"duration_ms": 119888,
|
667 |
+
"time_to_first_token_ms": {
|
668 |
+
"p50": 58.122,
|
669 |
+
"p60": 63.978,
|
670 |
+
"p70": 70.049,
|
671 |
+
"p80": 76.219,
|
672 |
+
"p90": 82.824,
|
673 |
+
"p95": 86.111,
|
674 |
+
"p99": 90.923,
|
675 |
+
"avg": 59.703
|
676 |
+
},
|
677 |
+
"inter_token_latency_ms": {
|
678 |
+
"p50": 29.32,
|
679 |
+
"p60": 29.492,
|
680 |
+
"p70": 29.895,
|
681 |
+
"p80": 30.4,
|
682 |
+
"p90": 30.546,
|
683 |
+
"p95": 31.209,
|
684 |
+
"p99": 31.92,
|
685 |
+
"avg": 28.595
|
686 |
+
},
|
687 |
+
"failed_requests": 0,
|
688 |
+
"successful_requests": 2290,
|
689 |
+
"request_rate": 19.10115725844384,
|
690 |
+
"total_tokens_sent": 346259,
|
691 |
+
"e2e_latency_ms": {
|
692 |
+
"p50": 5821.093,
|
693 |
+
"p60": 5905.813,
|
694 |
+
"p70": 5981.542,
|
695 |
+
"p80": 6088.576,
|
696 |
+
"p90": 6138.484,
|
697 |
+
"p95": 6172.066,
|
698 |
+
"p99": 6421.6,
|
699 |
+
"avg": 4983.079
|
700 |
+
}
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"id": "[email protected]/s",
|
704 |
+
"executor_type": "ConstantArrivalRate",
|
705 |
+
"config": {
|
706 |
+
"max_vus": 128,
|
707 |
+
"duration_secs": 120,
|
708 |
+
"rate": 21.6
|
709 |
+
},
|
710 |
+
"total_requests": 2445,
|
711 |
+
"total_tokens": 438323,
|
712 |
+
"token_throughput_secs": 3667.2404231554137,
|
713 |
+
"duration_ms": 119523,
|
714 |
+
"time_to_first_token_ms": {
|
715 |
+
"p50": 60.891,
|
716 |
+
"p60": 67.221,
|
717 |
+
"p70": 73.352,
|
718 |
+
"p80": 80.009,
|
719 |
+
"p90": 86.246,
|
720 |
+
"p95": 89.966,
|
721 |
+
"p99": 95.937,
|
722 |
+
"avg": 62.545
|
723 |
+
},
|
724 |
+
"inter_token_latency_ms": {
|
725 |
+
"p50": 31.059,
|
726 |
+
"p60": 31.174,
|
727 |
+
"p70": 31.267,
|
728 |
+
"p80": 31.363,
|
729 |
+
"p90": 31.564,
|
730 |
+
"p95": 31.98,
|
731 |
+
"p99": 32.368,
|
732 |
+
"avg": 30.585
|
733 |
+
},
|
734 |
+
"failed_requests": 0,
|
735 |
+
"successful_requests": 2445,
|
736 |
+
"request_rate": 20.456154102374246,
|
737 |
+
"total_tokens_sent": 375764,
|
738 |
+
"e2e_latency_ms": {
|
739 |
+
"p50": 6210.518,
|
740 |
+
"p60": 6251.837,
|
741 |
+
"p70": 6276.884,
|
742 |
+
"p80": 6301.657,
|
743 |
+
"p90": 6339.383,
|
744 |
+
"p95": 6390.942,
|
745 |
+
"p99": 6504.767,
|
746 |
+
"avg": 5545.311
|
747 |
+
}
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"id": "[email protected]/s",
|
751 |
+
"executor_type": "ConstantArrivalRate",
|
752 |
+
"config": {
|
753 |
+
"max_vus": 128,
|
754 |
+
"duration_secs": 120,
|
755 |
+
"rate": 23.2
|
756 |
+
},
|
757 |
+
"total_requests": 2557,
|
758 |
+
"total_tokens": 451146,
|
759 |
+
"token_throughput_secs": 3774.5098883710634,
|
760 |
+
"duration_ms": 119524,
|
761 |
+
"time_to_first_token_ms": {
|
762 |
+
"p50": 61.047,
|
763 |
+
"p60": 67.493,
|
764 |
+
"p70": 74.009,
|
765 |
+
"p80": 80.579,
|
766 |
+
"p90": 87.143,
|
767 |
+
"p95": 90.788,
|
768 |
+
"p99": 95.729,
|
769 |
+
"avg": 63.122
|
770 |
+
},
|
771 |
+
"inter_token_latency_ms": {
|
772 |
+
"p50": 31.013,
|
773 |
+
"p60": 31.094,
|
774 |
+
"p70": 31.187,
|
775 |
+
"p80": 31.29,
|
776 |
+
"p90": 31.621,
|
777 |
+
"p95": 32.321,
|
778 |
+
"p99": 32.547,
|
779 |
+
"avg": 30.814
|
780 |
+
},
|
781 |
+
"failed_requests": 0,
|
782 |
+
"successful_requests": 2557,
|
783 |
+
"request_rate": 21.393122812935964,
|
784 |
+
"total_tokens_sent": 397220,
|
785 |
+
"e2e_latency_ms": {
|
786 |
+
"p50": 6207.811,
|
787 |
+
"p60": 6232.278,
|
788 |
+
"p70": 6255.491,
|
789 |
+
"p80": 6280.109,
|
790 |
+
"p90": 6327.14,
|
791 |
+
"p95": 6467.71,
|
792 |
+
"p99": 6530.251,
|
793 |
+
"avg": 5488.01
|
794 |
+
}
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"id": "[email protected]/s",
|
798 |
+
"executor_type": "ConstantArrivalRate",
|
799 |
+
"config": {
|
800 |
+
"max_vus": 128,
|
801 |
+
"duration_secs": 120,
|
802 |
+
"rate": 24.0
|
803 |
+
},
|
804 |
+
"total_requests": 2540,
|
805 |
+
"total_tokens": 454462,
|
806 |
+
"token_throughput_secs": 3793.8392202012997,
|
807 |
+
"duration_ms": 119789,
|
808 |
+
"time_to_first_token_ms": {
|
809 |
+
"p50": 61.504,
|
810 |
+
"p60": 67.687,
|
811 |
+
"p70": 74.328,
|
812 |
+
"p80": 81.247,
|
813 |
+
"p90": 87.806,
|
814 |
+
"p95": 91.29,
|
815 |
+
"p99": 96.912,
|
816 |
+
"avg": 63.516
|
817 |
+
},
|
818 |
+
"inter_token_latency_ms": {
|
819 |
+
"p50": 31.192,
|
820 |
+
"p60": 31.251,
|
821 |
+
"p70": 31.333,
|
822 |
+
"p80": 31.475,
|
823 |
+
"p90": 31.907,
|
824 |
+
"p95": 32.12,
|
825 |
+
"p99": 32.242,
|
826 |
+
"avg": 30.921
|
827 |
+
},
|
828 |
+
"failed_requests": 0,
|
829 |
+
"successful_requests": 2540,
|
830 |
+
"request_rate": 21.203866592391226,
|
831 |
+
"total_tokens_sent": 455432,
|
832 |
+
"e2e_latency_ms": {
|
833 |
+
"p50": 6257.817,
|
834 |
+
"p60": 6275.79,
|
835 |
+
"p70": 6293.476,
|
836 |
+
"p80": 6317.243,
|
837 |
+
"p90": 6372.71,
|
838 |
+
"p95": 6449.819,
|
839 |
+
"p99": 6483.148,
|
840 |
+
"avg": 5596.165
|
841 |
+
}
|
842 |
+
}
|
843 |
+
],
|
844 |
+
"start_time": "2025-04-02T07:17:06.471305459+00:00",
|
845 |
+
"end_time": "2025-04-02T07:50:23.157564514+00:00",
|
846 |
+
"system": {
|
847 |
+
"cpu": [
|
848 |
+
"AMD EPYC 7R13 Processor cpu0@2649MHz",
|
849 |
+
"AMD EPYC 7R13 Processor cpu1@2516MHz",
|
850 |
+
"AMD EPYC 7R13 Processor cpu2@2516MHz",
|
851 |
+
"AMD EPYC 7R13 Processor cpu3@2649MHz",
|
852 |
+
"AMD EPYC 7R13 Processor cpu4@2516MHz",
|
853 |
+
"AMD EPYC 7R13 Processor cpu5@2516MHz",
|
854 |
+
"AMD EPYC 7R13 Processor cpu6@2516MHz",
|
855 |
+
"AMD EPYC 7R13 Processor cpu7@2649MHz",
|
856 |
+
"AMD EPYC 7R13 Processor cpu8@2649MHz",
|
857 |
+
"AMD EPYC 7R13 Processor cpu9@2649MHz",
|
858 |
+
"AMD EPYC 7R13 Processor cpu10@2649MHz",
|
859 |
+
"AMD EPYC 7R13 Processor cpu11@2649MHz",
|
860 |
+
"AMD EPYC 7R13 Processor cpu12@2516MHz",
|
861 |
+
"AMD EPYC 7R13 Processor cpu13@2881MHz",
|
862 |
+
"AMD EPYC 7R13 Processor cpu14@2516MHz",
|
863 |
+
"AMD EPYC 7R13 Processor cpu15@2649MHz",
|
864 |
+
"AMD EPYC 7R13 Processor cpu16@2649MHz",
|
865 |
+
"AMD EPYC 7R13 Processor cpu17@2649MHz",
|
866 |
+
"AMD EPYC 7R13 Processor cpu18@2516MHz",
|
867 |
+
"AMD EPYC 7R13 Processor cpu19@2516MHz",
|
868 |
+
"AMD EPYC 7R13 Processor cpu20@2516MHz",
|
869 |
+
"AMD EPYC 7R13 Processor cpu21@2516MHz",
|
870 |
+
"AMD EPYC 7R13 Processor cpu22@3083MHz",
|
871 |
+
"AMD EPYC 7R13 Processor cpu23@2649MHz",
|
872 |
+
"AMD EPYC 7R13 Processor cpu24@2516MHz",
|
873 |
+
"AMD EPYC 7R13 Processor cpu25@2516MHz",
|
874 |
+
"AMD EPYC 7R13 Processor cpu26@2516MHz",
|
875 |
+
"AMD EPYC 7R13 Processor cpu27@2516MHz",
|
876 |
+
"AMD EPYC 7R13 Processor cpu28@2649MHz",
|
877 |
+
"AMD EPYC 7R13 Processor cpu29@2516MHz",
|
878 |
+
"AMD EPYC 7R13 Processor cpu30@2516MHz",
|
879 |
+
"AMD EPYC 7R13 Processor cpu31@2516MHz",
|
880 |
+
"AMD EPYC 7R13 Processor cpu32@2516MHz",
|
881 |
+
"AMD EPYC 7R13 Processor cpu33@2516MHz",
|
882 |
+
"AMD EPYC 7R13 Processor cpu34@2649MHz",
|
883 |
+
"AMD EPYC 7R13 Processor cpu35@2649MHz",
|
884 |
+
"AMD EPYC 7R13 Processor cpu36@2516MHz",
|
885 |
+
"AMD EPYC 7R13 Processor cpu37@2516MHz",
|
886 |
+
"AMD EPYC 7R13 Processor cpu38@2516MHz",
|
887 |
+
"AMD EPYC 7R13 Processor cpu39@2649MHz",
|
888 |
+
"AMD EPYC 7R13 Processor cpu40@2649MHz",
|
889 |
+
"AMD EPYC 7R13 Processor cpu41@2649MHz",
|
890 |
+
"AMD EPYC 7R13 Processor cpu42@2516MHz",
|
891 |
+
"AMD EPYC 7R13 Processor cpu43@2516MHz",
|
892 |
+
"AMD EPYC 7R13 Processor cpu44@2881MHz",
|
893 |
+
"AMD EPYC 7R13 Processor cpu45@2516MHz",
|
894 |
+
"AMD EPYC 7R13 Processor cpu46@2516MHz",
|
895 |
+
"AMD EPYC 7R13 Processor cpu47@2649MHz",
|
896 |
+
"AMD EPYC 7R13 Processor cpu48@2516MHz",
|
897 |
+
"AMD EPYC 7R13 Processor cpu49@2516MHz",
|
898 |
+
"AMD EPYC 7R13 Processor cpu50@2516MHz",
|
899 |
+
"AMD EPYC 7R13 Processor cpu51@2649MHz",
|
900 |
+
"AMD EPYC 7R13 Processor cpu52@2649MHz",
|
901 |
+
"AMD EPYC 7R13 Processor cpu53@2649MHz",
|
902 |
+
"AMD EPYC 7R13 Processor cpu54@2516MHz",
|
903 |
+
"AMD EPYC 7R13 Processor cpu55@2516MHz",
|
904 |
+
"AMD EPYC 7R13 Processor cpu56@2516MHz",
|
905 |
+
"AMD EPYC 7R13 Processor cpu57@2516MHz",
|
906 |
+
"AMD EPYC 7R13 Processor cpu58@2516MHz",
|
907 |
+
"AMD EPYC 7R13 Processor cpu59@2516MHz",
|
908 |
+
"AMD EPYC 7R13 Processor cpu60@2516MHz",
|
909 |
+
"AMD EPYC 7R13 Processor cpu61@2516MHz",
|
910 |
+
"AMD EPYC 7R13 Processor cpu62@3007MHz",
|
911 |
+
"AMD EPYC 7R13 Processor cpu63@2649MHz",
|
912 |
+
"AMD EPYC 7R13 Processor cpu64@2649MHz",
|
913 |
+
"AMD EPYC 7R13 Processor cpu65@2649MHz",
|
914 |
+
"AMD EPYC 7R13 Processor cpu66@2649MHz",
|
915 |
+
"AMD EPYC 7R13 Processor cpu67@2649MHz",
|
916 |
+
"AMD EPYC 7R13 Processor cpu68@2649MHz",
|
917 |
+
"AMD EPYC 7R13 Processor cpu69@2649MHz",
|
918 |
+
"AMD EPYC 7R13 Processor cpu70@2649MHz",
|
919 |
+
"AMD EPYC 7R13 Processor cpu71@2649MHz",
|
920 |
+
"AMD EPYC 7R13 Processor cpu72@2649MHz",
|
921 |
+
"AMD EPYC 7R13 Processor cpu73@2649MHz",
|
922 |
+
"AMD EPYC 7R13 Processor cpu74@2649MHz",
|
923 |
+
"AMD EPYC 7R13 Processor cpu75@2649MHz",
|
924 |
+
"AMD EPYC 7R13 Processor cpu76@2649MHz",
|
925 |
+
"AMD EPYC 7R13 Processor cpu77@2649MHz",
|
926 |
+
"AMD EPYC 7R13 Processor cpu78@2516MHz",
|
927 |
+
"AMD EPYC 7R13 Processor cpu79@2516MHz",
|
928 |
+
"AMD EPYC 7R13 Processor cpu80@2516MHz",
|
929 |
+
"AMD EPYC 7R13 Processor cpu81@2649MHz",
|
930 |
+
"AMD EPYC 7R13 Processor cpu82@2649MHz",
|
931 |
+
"AMD EPYC 7R13 Processor cpu83@2649MHz",
|
932 |
+
"AMD EPYC 7R13 Processor cpu84@2516MHz",
|
933 |
+
"AMD EPYC 7R13 Processor cpu85@2516MHz",
|
934 |
+
"AMD EPYC 7R13 Processor cpu86@2649MHz",
|
935 |
+
"AMD EPYC 7R13 Processor cpu87@2649MHz",
|
936 |
+
"AMD EPYC 7R13 Processor cpu88@2649MHz",
|
937 |
+
"AMD EPYC 7R13 Processor cpu89@2649MHz",
|
938 |
+
"AMD EPYC 7R13 Processor cpu90@2649MHz",
|
939 |
+
"AMD EPYC 7R13 Processor cpu91@2649MHz",
|
940 |
+
"AMD EPYC 7R13 Processor cpu92@2649MHz",
|
941 |
+
"AMD EPYC 7R13 Processor cpu93@2649MHz",
|
942 |
+
"AMD EPYC 7R13 Processor cpu94@2649MHz",
|
943 |
+
"AMD EPYC 7R13 Processor cpu95@2649MHz"
|
944 |
+
],
|
945 |
+
"memory": "1999.99 GB",
|
946 |
+
"os_name": "Debian GNU/Linux",
|
947 |
+
"os_version": "11",
|
948 |
+
"kernel": "5.15.0-1048-aws",
|
949 |
+
"hostname": "ip-26-0-161-153"
|
950 |
+
}
|
951 |
+
}
|
results/meta-llama_Llama-3_1-8B-Instruct_2025-04-02-08-06-23.json
ADDED
@@ -0,0 +1,951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"max_vus": 128,
|
4 |
+
"duration_secs": 120,
|
5 |
+
"benchmark_kind": "Rate",
|
6 |
+
"warmup_duration_secs": 30,
|
7 |
+
"rates": [
|
8 |
+
0.8,
|
9 |
+
2.4,
|
10 |
+
4.0,
|
11 |
+
5.6,
|
12 |
+
7.2,
|
13 |
+
8.8,
|
14 |
+
10.4,
|
15 |
+
12.0,
|
16 |
+
13.6,
|
17 |
+
15.2,
|
18 |
+
16.8,
|
19 |
+
18.4,
|
20 |
+
20.0,
|
21 |
+
21.6,
|
22 |
+
23.2,
|
23 |
+
24.0
|
24 |
+
],
|
25 |
+
"num_rates": 10,
|
26 |
+
"prompt_options": null,
|
27 |
+
"decode_options": {
|
28 |
+
"num_tokens": 200,
|
29 |
+
"min_tokens": 200,
|
30 |
+
"max_tokens": 200,
|
31 |
+
"variance": 100
|
32 |
+
},
|
33 |
+
"tokenizer": "meta-llama/Llama-3.1-8B-Instruct",
|
34 |
+
"model_name": "meta-llama/Llama-3.1-8B-Instruct",
|
35 |
+
"profile": null,
|
36 |
+
"meta": {
|
37 |
+
"tp": "1",
|
38 |
+
"version": "d2ed52f531cf8098ca62375248e007022eaadc65",
|
39 |
+
"engine": "TGI"
|
40 |
+
},
|
41 |
+
"run_id": "TGI-2.4.1"
|
42 |
+
},
|
43 |
+
"results": [
|
44 |
+
{
|
45 |
+
"id": "warmup",
|
46 |
+
"executor_type": "ConstantVUs",
|
47 |
+
"config": {
|
48 |
+
"max_vus": 1,
|
49 |
+
"duration_secs": 30,
|
50 |
+
"rate": null
|
51 |
+
},
|
52 |
+
"total_requests": 21,
|
53 |
+
"total_tokens": 3526,
|
54 |
+
"token_throughput_secs": 122.88666224584397,
|
55 |
+
"duration_ms": 28693,
|
56 |
+
"time_to_first_token_ms": {
|
57 |
+
"p50": 46.249,
|
58 |
+
"p60": 46.647,
|
59 |
+
"p70": 47.564,
|
60 |
+
"p80": 48.066,
|
61 |
+
"p90": 48.771,
|
62 |
+
"p95": 84.208,
|
63 |
+
"p99": 86.256,
|
64 |
+
"avg": 49.712
|
65 |
+
},
|
66 |
+
"inter_token_latency_ms": {
|
67 |
+
"p50": 7.881,
|
68 |
+
"p60": 7.884,
|
69 |
+
"p70": 7.887,
|
70 |
+
"p80": 7.912,
|
71 |
+
"p90": 7.984,
|
72 |
+
"p95": 7.986,
|
73 |
+
"p99": 7.999,
|
74 |
+
"avg": 7.821
|
75 |
+
},
|
76 |
+
"failed_requests": 0,
|
77 |
+
"successful_requests": 21,
|
78 |
+
"request_rate": 0.7318831273859113,
|
79 |
+
"total_tokens_sent": 1337,
|
80 |
+
"e2e_latency_ms": {
|
81 |
+
"p50": 1614.476,
|
82 |
+
"p60": 1615.106,
|
83 |
+
"p70": 1615.452,
|
84 |
+
"p80": 1619.496,
|
85 |
+
"p90": 1634.138,
|
86 |
+
"p95": 1637.031,
|
87 |
+
"p99": 1668.807,
|
88 |
+
"avg": 1366.18
|
89 |
+
}
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"id": "[email protected]/s",
|
93 |
+
"executor_type": "ConstantArrivalRate",
|
94 |
+
"config": {
|
95 |
+
"max_vus": 128,
|
96 |
+
"duration_secs": 120,
|
97 |
+
"rate": 0.8
|
98 |
+
},
|
99 |
+
"total_requests": 94,
|
100 |
+
"total_tokens": 17800,
|
101 |
+
"token_throughput_secs": 150.94862460675677,
|
102 |
+
"duration_ms": 117920,
|
103 |
+
"time_to_first_token_ms": {
|
104 |
+
"p50": 24.484,
|
105 |
+
"p60": 25.247,
|
106 |
+
"p70": 26.255,
|
107 |
+
"p80": 27.172,
|
108 |
+
"p90": 28.51,
|
109 |
+
"p95": 29.611,
|
110 |
+
"p99": 30.397,
|
111 |
+
"avg": 24.771
|
112 |
+
},
|
113 |
+
"inter_token_latency_ms": {
|
114 |
+
"p50": 8.272,
|
115 |
+
"p60": 8.28,
|
116 |
+
"p70": 8.286,
|
117 |
+
"p80": 8.292,
|
118 |
+
"p90": 8.326,
|
119 |
+
"p95": 8.376,
|
120 |
+
"p99": 8.475,
|
121 |
+
"avg": 8.281
|
122 |
+
},
|
123 |
+
"failed_requests": 0,
|
124 |
+
"successful_requests": 94,
|
125 |
+
"request_rate": 0.7971444220806255,
|
126 |
+
"total_tokens_sent": 11826,
|
127 |
+
"e2e_latency_ms": {
|
128 |
+
"p50": 1670.039,
|
129 |
+
"p60": 1671.341,
|
130 |
+
"p70": 1673.034,
|
131 |
+
"p80": 1675.422,
|
132 |
+
"p90": 1677.624,
|
133 |
+
"p95": 1684.827,
|
134 |
+
"p99": 1704.448,
|
135 |
+
"avg": 1584.628
|
136 |
+
}
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"id": "[email protected]/s",
|
140 |
+
"executor_type": "ConstantArrivalRate",
|
141 |
+
"config": {
|
142 |
+
"max_vus": 128,
|
143 |
+
"duration_secs": 120,
|
144 |
+
"rate": 2.4
|
145 |
+
},
|
146 |
+
"total_requests": 284,
|
147 |
+
"total_tokens": 48304,
|
148 |
+
"token_throughput_secs": 406.254834027723,
|
149 |
+
"duration_ms": 118900,
|
150 |
+
"time_to_first_token_ms": {
|
151 |
+
"p50": 25.492,
|
152 |
+
"p60": 26.266,
|
153 |
+
"p70": 27.157,
|
154 |
+
"p80": 28.116,
|
155 |
+
"p90": 29.53,
|
156 |
+
"p95": 30.532,
|
157 |
+
"p99": 46.87,
|
158 |
+
"avg": 26.066
|
159 |
+
},
|
160 |
+
"inter_token_latency_ms": {
|
161 |
+
"p50": 8.977,
|
162 |
+
"p60": 9.004,
|
163 |
+
"p70": 9.027,
|
164 |
+
"p80": 9.052,
|
165 |
+
"p90": 9.082,
|
166 |
+
"p95": 9.114,
|
167 |
+
"p99": 9.179,
|
168 |
+
"avg": 8.716
|
169 |
+
},
|
170 |
+
"failed_requests": 0,
|
171 |
+
"successful_requests": 284,
|
172 |
+
"request_rate": 2.3885469705174174,
|
173 |
+
"total_tokens_sent": 43082,
|
174 |
+
"e2e_latency_ms": {
|
175 |
+
"p50": 1809.698,
|
176 |
+
"p60": 1814.702,
|
177 |
+
"p70": 1820.864,
|
178 |
+
"p80": 1827.06,
|
179 |
+
"p90": 1833.784,
|
180 |
+
"p95": 1838.2,
|
181 |
+
"p99": 1849.697,
|
182 |
+
"avg": 1543.709
|
183 |
+
}
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"id": "[email protected]/s",
|
187 |
+
"executor_type": "ConstantArrivalRate",
|
188 |
+
"config": {
|
189 |
+
"max_vus": 128,
|
190 |
+
"duration_secs": 120,
|
191 |
+
"rate": 4.0
|
192 |
+
},
|
193 |
+
"total_requests": 472,
|
194 |
+
"total_tokens": 83257,
|
195 |
+
"token_throughput_secs": 697.279766847058,
|
196 |
+
"duration_ms": 119402,
|
197 |
+
"time_to_first_token_ms": {
|
198 |
+
"p50": 25.684,
|
199 |
+
"p60": 26.779,
|
200 |
+
"p70": 27.553,
|
201 |
+
"p80": 28.486,
|
202 |
+
"p90": 29.463,
|
203 |
+
"p95": 30.455,
|
204 |
+
"p99": 45.113,
|
205 |
+
"avg": 26.146
|
206 |
+
},
|
207 |
+
"inter_token_latency_ms": {
|
208 |
+
"p50": 9.418,
|
209 |
+
"p60": 9.445,
|
210 |
+
"p70": 9.461,
|
211 |
+
"p80": 9.49,
|
212 |
+
"p90": 9.526,
|
213 |
+
"p95": 9.532,
|
214 |
+
"p99": 9.547,
|
215 |
+
"avg": 9.371
|
216 |
+
},
|
217 |
+
"failed_requests": 0,
|
218 |
+
"successful_requests": 472,
|
219 |
+
"request_rate": 3.953013559842552,
|
220 |
+
"total_tokens_sent": 53690,
|
221 |
+
"e2e_latency_ms": {
|
222 |
+
"p50": 1898.831,
|
223 |
+
"p60": 1904.467,
|
224 |
+
"p70": 1907.994,
|
225 |
+
"p80": 1913.596,
|
226 |
+
"p90": 1920.946,
|
227 |
+
"p95": 1923.942,
|
228 |
+
"p99": 1928.04,
|
229 |
+
"avg": 1679.7
|
230 |
+
}
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"id": "[email protected]/s",
|
234 |
+
"executor_type": "ConstantArrivalRate",
|
235 |
+
"config": {
|
236 |
+
"max_vus": 128,
|
237 |
+
"duration_secs": 120,
|
238 |
+
"rate": 5.6
|
239 |
+
},
|
240 |
+
"total_requests": 662,
|
241 |
+
"total_tokens": 118380,
|
242 |
+
"token_throughput_secs": 989.0969943504368,
|
243 |
+
"duration_ms": 119684,
|
244 |
+
"time_to_first_token_ms": {
|
245 |
+
"p50": 26.614,
|
246 |
+
"p60": 27.599,
|
247 |
+
"p70": 28.411,
|
248 |
+
"p80": 29.519,
|
249 |
+
"p90": 40.521,
|
250 |
+
"p95": 45.386,
|
251 |
+
"p99": 47.427,
|
252 |
+
"avg": 27.98
|
253 |
+
},
|
254 |
+
"inter_token_latency_ms": {
|
255 |
+
"p50": 9.948,
|
256 |
+
"p60": 9.96,
|
257 |
+
"p70": 9.969,
|
258 |
+
"p80": 9.98,
|
259 |
+
"p90": 9.995,
|
260 |
+
"p95": 10.005,
|
261 |
+
"p99": 10.037,
|
262 |
+
"avg": 9.848
|
263 |
+
},
|
264 |
+
"failed_requests": 0,
|
265 |
+
"successful_requests": 662,
|
266 |
+
"request_rate": 5.531189476769633,
|
267 |
+
"total_tokens_sent": 111696,
|
268 |
+
"e2e_latency_ms": {
|
269 |
+
"p50": 2004.271,
|
270 |
+
"p60": 2007.295,
|
271 |
+
"p70": 2010.406,
|
272 |
+
"p80": 2012.985,
|
273 |
+
"p90": 2015.977,
|
274 |
+
"p95": 2017.766,
|
275 |
+
"p99": 2025.136,
|
276 |
+
"avg": 1791.085
|
277 |
+
}
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"id": "[email protected]/s",
|
281 |
+
"executor_type": "ConstantArrivalRate",
|
282 |
+
"config": {
|
283 |
+
"max_vus": 128,
|
284 |
+
"duration_secs": 120,
|
285 |
+
"rate": 7.2
|
286 |
+
},
|
287 |
+
"total_requests": 850,
|
288 |
+
"total_tokens": 150442,
|
289 |
+
"token_throughput_secs": 1255.1886063661461,
|
290 |
+
"duration_ms": 119856,
|
291 |
+
"time_to_first_token_ms": {
|
292 |
+
"p50": 42.393,
|
293 |
+
"p60": 44.487,
|
294 |
+
"p70": 45.999,
|
295 |
+
"p80": 46.482,
|
296 |
+
"p90": 47.894,
|
297 |
+
"p95": 48.207,
|
298 |
+
"p99": 48.37,
|
299 |
+
"avg": 37.807
|
300 |
+
},
|
301 |
+
"inter_token_latency_ms": {
|
302 |
+
"p50": 10.186,
|
303 |
+
"p60": 10.207,
|
304 |
+
"p70": 10.229,
|
305 |
+
"p80": 10.259,
|
306 |
+
"p90": 10.316,
|
307 |
+
"p95": 10.336,
|
308 |
+
"p99": 10.359,
|
309 |
+
"avg": 9.933
|
310 |
+
},
|
311 |
+
"failed_requests": 0,
|
312 |
+
"successful_requests": 850,
|
313 |
+
"request_rate": 7.091838152984034,
|
314 |
+
"total_tokens_sent": 168386,
|
315 |
+
"e2e_latency_ms": {
|
316 |
+
"p50": 2065.737,
|
317 |
+
"p60": 2070.244,
|
318 |
+
"p70": 2074.586,
|
319 |
+
"p80": 2078.847,
|
320 |
+
"p90": 2083.084,
|
321 |
+
"p95": 2085.846,
|
322 |
+
"p99": 2094.979,
|
323 |
+
"avg": 1832.984
|
324 |
+
}
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"id": "[email protected]/s",
|
328 |
+
"executor_type": "ConstantArrivalRate",
|
329 |
+
"config": {
|
330 |
+
"max_vus": 128,
|
331 |
+
"duration_secs": 120,
|
332 |
+
"rate": 8.8
|
333 |
+
},
|
334 |
+
"total_requests": 1044,
|
335 |
+
"total_tokens": 189381,
|
336 |
+
"token_throughput_secs": 1581.3245632308367,
|
337 |
+
"duration_ms": 119760,
|
338 |
+
"time_to_first_token_ms": {
|
339 |
+
"p50": 42.904,
|
340 |
+
"p60": 44.702,
|
341 |
+
"p70": 45.143,
|
342 |
+
"p80": 45.649,
|
343 |
+
"p90": 47.202,
|
344 |
+
"p95": 47.429,
|
345 |
+
"p99": 47.647,
|
346 |
+
"avg": 38.138
|
347 |
+
},
|
348 |
+
"inter_token_latency_ms": {
|
349 |
+
"p50": 10.601,
|
350 |
+
"p60": 10.617,
|
351 |
+
"p70": 10.64,
|
352 |
+
"p80": 10.669,
|
353 |
+
"p90": 10.709,
|
354 |
+
"p95": 10.745,
|
355 |
+
"p99": 10.837,
|
356 |
+
"avg": 10.457
|
357 |
+
},
|
358 |
+
"failed_requests": 0,
|
359 |
+
"successful_requests": 1044,
|
360 |
+
"request_rate": 8.717362586600522,
|
361 |
+
"total_tokens_sent": 164348,
|
362 |
+
"e2e_latency_ms": {
|
363 |
+
"p50": 2149.601,
|
364 |
+
"p60": 2152.628,
|
365 |
+
"p70": 2155.129,
|
366 |
+
"p80": 2157.878,
|
367 |
+
"p90": 2161.992,
|
368 |
+
"p95": 2166.405,
|
369 |
+
"p99": 2185.247,
|
370 |
+
"avg": 1952.745
|
371 |
+
}
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"id": "[email protected]/s",
|
375 |
+
"executor_type": "ConstantArrivalRate",
|
376 |
+
"config": {
|
377 |
+
"max_vus": 128,
|
378 |
+
"duration_secs": 120,
|
379 |
+
"rate": 10.4
|
380 |
+
},
|
381 |
+
"total_requests": 1227,
|
382 |
+
"total_tokens": 215756,
|
383 |
+
"token_throughput_secs": 1801.727543102545,
|
384 |
+
"duration_ms": 119749,
|
385 |
+
"time_to_first_token_ms": {
|
386 |
+
"p50": 28.996,
|
387 |
+
"p60": 29.94,
|
388 |
+
"p70": 31.219,
|
389 |
+
"p80": 33.038,
|
390 |
+
"p90": 43.255,
|
391 |
+
"p95": 45.051,
|
392 |
+
"p99": 47.322,
|
393 |
+
"avg": 30.686
|
394 |
+
},
|
395 |
+
"inter_token_latency_ms": {
|
396 |
+
"p50": 11.152,
|
397 |
+
"p60": 11.172,
|
398 |
+
"p70": 11.192,
|
399 |
+
"p80": 11.214,
|
400 |
+
"p90": 11.247,
|
401 |
+
"p95": 11.271,
|
402 |
+
"p99": 11.413,
|
403 |
+
"avg": 11.041
|
404 |
+
},
|
405 |
+
"failed_requests": 0,
|
406 |
+
"successful_requests": 1227,
|
407 |
+
"request_rate": 10.246388028081828,
|
408 |
+
"total_tokens_sent": 216589,
|
409 |
+
"e2e_latency_ms": {
|
410 |
+
"p50": 2246.941,
|
411 |
+
"p60": 2250.773,
|
412 |
+
"p70": 2254.922,
|
413 |
+
"p80": 2260.186,
|
414 |
+
"p90": 2267.355,
|
415 |
+
"p95": 2272.509,
|
416 |
+
"p99": 2299.613,
|
417 |
+
"avg": 1980.137
|
418 |
+
}
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"id": "[email protected]/s",
|
422 |
+
"executor_type": "ConstantArrivalRate",
|
423 |
+
"config": {
|
424 |
+
"max_vus": 128,
|
425 |
+
"duration_secs": 120,
|
426 |
+
"rate": 12.0
|
427 |
+
},
|
428 |
+
"total_requests": 1413,
|
429 |
+
"total_tokens": 257715,
|
430 |
+
"token_throughput_secs": 2152.3457887331883,
|
431 |
+
"duration_ms": 119736,
|
432 |
+
"time_to_first_token_ms": {
|
433 |
+
"p50": 32.129,
|
434 |
+
"p60": 41.129,
|
435 |
+
"p70": 42.905,
|
436 |
+
"p80": 43.618,
|
437 |
+
"p90": 45.582,
|
438 |
+
"p95": 47.077,
|
439 |
+
"p99": 47.609,
|
440 |
+
"avg": 34.989
|
441 |
+
},
|
442 |
+
"inter_token_latency_ms": {
|
443 |
+
"p50": 11.524,
|
444 |
+
"p60": 11.571,
|
445 |
+
"p70": 11.619,
|
446 |
+
"p80": 11.681,
|
447 |
+
"p90": 11.737,
|
448 |
+
"p95": 11.759,
|
449 |
+
"p99": 11.825,
|
450 |
+
"avg": 11.473
|
451 |
+
},
|
452 |
+
"failed_requests": 0,
|
453 |
+
"successful_requests": 1413,
|
454 |
+
"request_rate": 11.800883144093262,
|
455 |
+
"total_tokens_sent": 224022,
|
456 |
+
"e2e_latency_ms": {
|
457 |
+
"p50": 2327.912,
|
458 |
+
"p60": 2333.025,
|
459 |
+
"p70": 2339.512,
|
460 |
+
"p80": 2355.095,
|
461 |
+
"p90": 2364.745,
|
462 |
+
"p95": 2369.454,
|
463 |
+
"p99": 2381.415,
|
464 |
+
"avg": 2131.083
|
465 |
+
}
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"id": "[email protected]/s",
|
469 |
+
"executor_type": "ConstantArrivalRate",
|
470 |
+
"config": {
|
471 |
+
"max_vus": 128,
|
472 |
+
"duration_secs": 120,
|
473 |
+
"rate": 13.6
|
474 |
+
},
|
475 |
+
"total_requests": 1586,
|
476 |
+
"total_tokens": 273066,
|
477 |
+
"token_throughput_secs": 2286.726108001893,
|
478 |
+
"duration_ms": 119413,
|
479 |
+
"time_to_first_token_ms": {
|
480 |
+
"p50": 41.765,
|
481 |
+
"p60": 43.496,
|
482 |
+
"p70": 45.121,
|
483 |
+
"p80": 45.647,
|
484 |
+
"p90": 47.119,
|
485 |
+
"p95": 47.381,
|
486 |
+
"p99": 47.644,
|
487 |
+
"avg": 39.252
|
488 |
+
},
|
489 |
+
"inter_token_latency_ms": {
|
490 |
+
"p50": 21.018,
|
491 |
+
"p60": 21.058,
|
492 |
+
"p70": 21.094,
|
493 |
+
"p80": 21.136,
|
494 |
+
"p90": 21.204,
|
495 |
+
"p95": 21.361,
|
496 |
+
"p99": 21.474,
|
497 |
+
"avg": 20.088
|
498 |
+
},
|
499 |
+
"failed_requests": 0,
|
500 |
+
"successful_requests": 1586,
|
501 |
+
"request_rate": 13.281578839148787,
|
502 |
+
"total_tokens_sent": 263160,
|
503 |
+
"e2e_latency_ms": {
|
504 |
+
"p50": 4215.628,
|
505 |
+
"p60": 4224.579,
|
506 |
+
"p70": 4233.564,
|
507 |
+
"p80": 4241.334,
|
508 |
+
"p90": 4253.157,
|
509 |
+
"p95": 4281.605,
|
510 |
+
"p99": 4307.594,
|
511 |
+
"avg": 3499.01
|
512 |
+
}
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"id": "[email protected]/s",
|
516 |
+
"executor_type": "ConstantArrivalRate",
|
517 |
+
"config": {
|
518 |
+
"max_vus": 128,
|
519 |
+
"duration_secs": 120,
|
520 |
+
"rate": 15.2
|
521 |
+
},
|
522 |
+
"total_requests": 1767,
|
523 |
+
"total_tokens": 318782,
|
524 |
+
"token_throughput_secs": 2659.660245067388,
|
525 |
+
"duration_ms": 119858,
|
526 |
+
"time_to_first_token_ms": {
|
527 |
+
"p50": 41.941,
|
528 |
+
"p60": 42.561,
|
529 |
+
"p70": 43.982,
|
530 |
+
"p80": 44.599,
|
531 |
+
"p90": 46.402,
|
532 |
+
"p95": 47.889,
|
533 |
+
"p99": 48.314,
|
534 |
+
"avg": 38.969
|
535 |
+
},
|
536 |
+
"inter_token_latency_ms": {
|
537 |
+
"p50": 21.711,
|
538 |
+
"p60": 21.755,
|
539 |
+
"p70": 21.812,
|
540 |
+
"p80": 21.867,
|
541 |
+
"p90": 21.933,
|
542 |
+
"p95": 21.976,
|
543 |
+
"p99": 22.027,
|
544 |
+
"avg": 21.316
|
545 |
+
},
|
546 |
+
"failed_requests": 0,
|
547 |
+
"successful_requests": 1767,
|
548 |
+
"request_rate": 14.742424770012343,
|
549 |
+
"total_tokens_sent": 299995,
|
550 |
+
"e2e_latency_ms": {
|
551 |
+
"p50": 4354.219,
|
552 |
+
"p60": 4361.816,
|
553 |
+
"p70": 4377.337,
|
554 |
+
"p80": 4389.415,
|
555 |
+
"p90": 4402.615,
|
556 |
+
"p95": 4409.06,
|
557 |
+
"p99": 4416.879,
|
558 |
+
"avg": 3900.022
|
559 |
+
}
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"id": "[email protected]/s",
|
563 |
+
"executor_type": "ConstantArrivalRate",
|
564 |
+
"config": {
|
565 |
+
"max_vus": 128,
|
566 |
+
"duration_secs": 120,
|
567 |
+
"rate": 16.8
|
568 |
+
},
|
569 |
+
"total_requests": 1952,
|
570 |
+
"total_tokens": 349899,
|
571 |
+
"token_throughput_secs": 2924.5946715959903,
|
572 |
+
"duration_ms": 119640,
|
573 |
+
"time_to_first_token_ms": {
|
574 |
+
"p50": 42.018,
|
575 |
+
"p60": 42.508,
|
576 |
+
"p70": 43.793,
|
577 |
+
"p80": 44.153,
|
578 |
+
"p90": 44.83,
|
579 |
+
"p95": 46.44,
|
580 |
+
"p99": 48.232,
|
581 |
+
"avg": 38.955
|
582 |
+
},
|
583 |
+
"inter_token_latency_ms": {
|
584 |
+
"p50": 22.202,
|
585 |
+
"p60": 22.257,
|
586 |
+
"p70": 22.348,
|
587 |
+
"p80": 22.464,
|
588 |
+
"p90": 22.555,
|
589 |
+
"p95": 22.618,
|
590 |
+
"p99": 22.716,
|
591 |
+
"avg": 21.964
|
592 |
+
},
|
593 |
+
"failed_requests": 0,
|
594 |
+
"successful_requests": 1952,
|
595 |
+
"request_rate": 16.315590495987053,
|
596 |
+
"total_tokens_sent": 308143,
|
597 |
+
"e2e_latency_ms": {
|
598 |
+
"p50": 4448.481,
|
599 |
+
"p60": 4462.093,
|
600 |
+
"p70": 4478.598,
|
601 |
+
"p80": 4507.043,
|
602 |
+
"p90": 4525.206,
|
603 |
+
"p95": 4538.11,
|
604 |
+
"p99": 4560.079,
|
605 |
+
"avg": 3971.144
|
606 |
+
}
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"id": "[email protected]/s",
|
610 |
+
"executor_type": "ConstantArrivalRate",
|
611 |
+
"config": {
|
612 |
+
"max_vus": 128,
|
613 |
+
"duration_secs": 120,
|
614 |
+
"rate": 18.4
|
615 |
+
},
|
616 |
+
"total_requests": 2135,
|
617 |
+
"total_tokens": 377085,
|
618 |
+
"token_throughput_secs": 3157.5918029420154,
|
619 |
+
"duration_ms": 119421,
|
620 |
+
"time_to_first_token_ms": {
|
621 |
+
"p50": 42.037,
|
622 |
+
"p60": 42.627,
|
623 |
+
"p70": 43.838,
|
624 |
+
"p80": 44.183,
|
625 |
+
"p90": 45.567,
|
626 |
+
"p95": 46.603,
|
627 |
+
"p99": 48.266,
|
628 |
+
"avg": 39.44
|
629 |
+
},
|
630 |
+
"inter_token_latency_ms": {
|
631 |
+
"p50": 22.519,
|
632 |
+
"p60": 22.586,
|
633 |
+
"p70": 22.678,
|
634 |
+
"p80": 22.785,
|
635 |
+
"p90": 22.851,
|
636 |
+
"p95": 22.888,
|
637 |
+
"p99": 22.962,
|
638 |
+
"avg": 22.143
|
639 |
+
},
|
640 |
+
"failed_requests": 0,
|
641 |
+
"successful_requests": 2135,
|
642 |
+
"request_rate": 17.87782197457126,
|
643 |
+
"total_tokens_sent": 378767,
|
644 |
+
"e2e_latency_ms": {
|
645 |
+
"p50": 4511.199,
|
646 |
+
"p60": 4525.581,
|
647 |
+
"p70": 4542.862,
|
648 |
+
"p80": 4569.463,
|
649 |
+
"p90": 4584.328,
|
650 |
+
"p95": 4592.49,
|
651 |
+
"p99": 4605.219,
|
652 |
+
"avg": 3978.179
|
653 |
+
}
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"id": "[email protected]/s",
|
657 |
+
"executor_type": "ConstantArrivalRate",
|
658 |
+
"config": {
|
659 |
+
"max_vus": 128,
|
660 |
+
"duration_secs": 120,
|
661 |
+
"rate": 20.0
|
662 |
+
},
|
663 |
+
"total_requests": 2314,
|
664 |
+
"total_tokens": 410851,
|
665 |
+
"token_throughput_secs": 3431.8999694521895,
|
666 |
+
"duration_ms": 119715,
|
667 |
+
"time_to_first_token_ms": {
|
668 |
+
"p50": 42.054,
|
669 |
+
"p60": 42.898,
|
670 |
+
"p70": 43.131,
|
671 |
+
"p80": 43.857,
|
672 |
+
"p90": 45.58,
|
673 |
+
"p95": 47.057,
|
674 |
+
"p99": 53.486,
|
675 |
+
"avg": 40.178
|
676 |
+
},
|
677 |
+
"inter_token_latency_ms": {
|
678 |
+
"p50": 23.178,
|
679 |
+
"p60": 23.241,
|
680 |
+
"p70": 23.306,
|
681 |
+
"p80": 23.362,
|
682 |
+
"p90": 23.489,
|
683 |
+
"p95": 23.649,
|
684 |
+
"p99": 24.696,
|
685 |
+
"avg": 22.962
|
686 |
+
},
|
687 |
+
"failed_requests": 0,
|
688 |
+
"successful_requests": 2314,
|
689 |
+
"request_rate": 19.329188755320946,
|
690 |
+
"total_tokens_sent": 428632,
|
691 |
+
"e2e_latency_ms": {
|
692 |
+
"p50": 4641.862,
|
693 |
+
"p60": 4658.169,
|
694 |
+
"p70": 4671.517,
|
695 |
+
"p80": 4685.088,
|
696 |
+
"p90": 4705.846,
|
697 |
+
"p95": 4725.362,
|
698 |
+
"p99": 4949.917,
|
699 |
+
"avg": 4118.614
|
700 |
+
}
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"id": "[email protected]/s",
|
704 |
+
"executor_type": "ConstantArrivalRate",
|
705 |
+
"config": {
|
706 |
+
"max_vus": 128,
|
707 |
+
"duration_secs": 120,
|
708 |
+
"rate": 21.6
|
709 |
+
},
|
710 |
+
"total_requests": 2496,
|
711 |
+
"total_tokens": 425184,
|
712 |
+
"token_throughput_secs": 3546.9270370066156,
|
713 |
+
"duration_ms": 119873,
|
714 |
+
"time_to_first_token_ms": {
|
715 |
+
"p50": 47.532,
|
716 |
+
"p60": 51.096,
|
717 |
+
"p70": 55.311,
|
718 |
+
"p80": 59.955,
|
719 |
+
"p90": 64.818,
|
720 |
+
"p95": 68.566,
|
721 |
+
"p99": 73.174,
|
722 |
+
"avg": 49.832
|
723 |
+
},
|
724 |
+
"inter_token_latency_ms": {
|
725 |
+
"p50": 23.615,
|
726 |
+
"p60": 23.819,
|
727 |
+
"p70": 23.937,
|
728 |
+
"p80": 24.142,
|
729 |
+
"p90": 24.335,
|
730 |
+
"p95": 24.424,
|
731 |
+
"p99": 24.675,
|
732 |
+
"avg": 23.117
|
733 |
+
},
|
734 |
+
"failed_requests": 0,
|
735 |
+
"successful_requests": 2496,
|
736 |
+
"request_rate": 20.821879196697225,
|
737 |
+
"total_tokens_sent": 449445,
|
738 |
+
"e2e_latency_ms": {
|
739 |
+
"p50": 4705.977,
|
740 |
+
"p60": 4760.663,
|
741 |
+
"p70": 4802.56,
|
742 |
+
"p80": 4835.503,
|
743 |
+
"p90": 4887.331,
|
744 |
+
"p95": 4911.378,
|
745 |
+
"p99": 4950.871,
|
746 |
+
"avg": 4041.088
|
747 |
+
}
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"id": "[email protected]/s",
|
751 |
+
"executor_type": "ConstantArrivalRate",
|
752 |
+
"config": {
|
753 |
+
"max_vus": 128,
|
754 |
+
"duration_secs": 120,
|
755 |
+
"rate": 23.2
|
756 |
+
},
|
757 |
+
"total_requests": 2693,
|
758 |
+
"total_tokens": 477598,
|
759 |
+
"token_throughput_secs": 3987.677624302409,
|
760 |
+
"duration_ms": 119768,
|
761 |
+
"time_to_first_token_ms": {
|
762 |
+
"p50": 48.917,
|
763 |
+
"p60": 53.875,
|
764 |
+
"p70": 58.427,
|
765 |
+
"p80": 63.212,
|
766 |
+
"p90": 68.231,
|
767 |
+
"p95": 71.137,
|
768 |
+
"p99": 75.227,
|
769 |
+
"avg": 51.515
|
770 |
+
},
|
771 |
+
"inter_token_latency_ms": {
|
772 |
+
"p50": 24.172,
|
773 |
+
"p60": 24.458,
|
774 |
+
"p70": 24.565,
|
775 |
+
"p80": 24.718,
|
776 |
+
"p90": 24.831,
|
777 |
+
"p95": 25.263,
|
778 |
+
"p99": 25.541,
|
779 |
+
"avg": 23.951
|
780 |
+
},
|
781 |
+
"failed_requests": 0,
|
782 |
+
"successful_requests": 2693,
|
783 |
+
"request_rate": 22.485051952157228,
|
784 |
+
"total_tokens_sent": 418148,
|
785 |
+
"e2e_latency_ms": {
|
786 |
+
"p50": 4820.55,
|
787 |
+
"p60": 4895.607,
|
788 |
+
"p70": 4932.562,
|
789 |
+
"p80": 4963.156,
|
790 |
+
"p90": 4990.976,
|
791 |
+
"p95": 5047.438,
|
792 |
+
"p99": 5133.803,
|
793 |
+
"avg": 4302.865
|
794 |
+
}
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"id": "[email protected]/s",
|
798 |
+
"executor_type": "ConstantArrivalRate",
|
799 |
+
"config": {
|
800 |
+
"max_vus": 128,
|
801 |
+
"duration_secs": 120,
|
802 |
+
"rate": 24.0
|
803 |
+
},
|
804 |
+
"total_requests": 2770,
|
805 |
+
"total_tokens": 491476,
|
806 |
+
"token_throughput_secs": 4122.591533026405,
|
807 |
+
"duration_ms": 119215,
|
808 |
+
"time_to_first_token_ms": {
|
809 |
+
"p50": 49.685,
|
810 |
+
"p60": 54.302,
|
811 |
+
"p70": 59.464,
|
812 |
+
"p80": 64.151,
|
813 |
+
"p90": 69.885,
|
814 |
+
"p95": 72.497,
|
815 |
+
"p99": 75.82,
|
816 |
+
"avg": 51.673
|
817 |
+
},
|
818 |
+
"inter_token_latency_ms": {
|
819 |
+
"p50": 24.572,
|
820 |
+
"p60": 24.655,
|
821 |
+
"p70": 24.758,
|
822 |
+
"p80": 24.89,
|
823 |
+
"p90": 25.177,
|
824 |
+
"p95": 25.712,
|
825 |
+
"p99": 25.93,
|
826 |
+
"avg": 24.429
|
827 |
+
},
|
828 |
+
"failed_requests": 0,
|
829 |
+
"successful_requests": 2770,
|
830 |
+
"request_rate": 23.235272010196105,
|
831 |
+
"total_tokens_sent": 417041,
|
832 |
+
"e2e_latency_ms": {
|
833 |
+
"p50": 4917.332,
|
834 |
+
"p60": 4944.149,
|
835 |
+
"p70": 4968.491,
|
836 |
+
"p80": 4997.781,
|
837 |
+
"p90": 5053.09,
|
838 |
+
"p95": 5149.163,
|
839 |
+
"p99": 5204.539,
|
840 |
+
"avg": 4376.615
|
841 |
+
}
|
842 |
+
}
|
843 |
+
],
|
844 |
+
"start_time": "2025-04-02T07:33:13.875090549+00:00",
|
845 |
+
"end_time": "2025-04-02T08:06:23.692065899+00:00",
|
846 |
+
"system": {
|
847 |
+
"cpu": [
|
848 |
+
"AMD EPYC 7R13 Processor cpu0@2363MHz",
|
849 |
+
"AMD EPYC 7R13 Processor cpu1@2649MHz",
|
850 |
+
"AMD EPYC 7R13 Processor cpu2@2673MHz",
|
851 |
+
"AMD EPYC 7R13 Processor cpu3@2673MHz",
|
852 |
+
"AMD EPYC 7R13 Processor cpu4@2649MHz",
|
853 |
+
"AMD EPYC 7R13 Processor cpu5@2673MHz",
|
854 |
+
"AMD EPYC 7R13 Processor cpu6@2673MHz",
|
855 |
+
"AMD EPYC 7R13 Processor cpu7@2649MHz",
|
856 |
+
"AMD EPYC 7R13 Processor cpu8@2649MHz",
|
857 |
+
"AMD EPYC 7R13 Processor cpu9@2673MHz",
|
858 |
+
"AMD EPYC 7R13 Processor cpu10@2673MHz",
|
859 |
+
"AMD EPYC 7R13 Processor cpu11@2673MHz",
|
860 |
+
"AMD EPYC 7R13 Processor cpu12@2649MHz",
|
861 |
+
"AMD EPYC 7R13 Processor cpu13@2673MHz",
|
862 |
+
"AMD EPYC 7R13 Processor cpu14@2673MHz",
|
863 |
+
"AMD EPYC 7R13 Processor cpu15@2673MHz",
|
864 |
+
"AMD EPYC 7R13 Processor cpu16@2673MHz",
|
865 |
+
"AMD EPYC 7R13 Processor cpu17@2673MHz",
|
866 |
+
"AMD EPYC 7R13 Processor cpu18@2673MHz",
|
867 |
+
"AMD EPYC 7R13 Processor cpu19@2649MHz",
|
868 |
+
"AMD EPYC 7R13 Processor cpu20@2649MHz",
|
869 |
+
"AMD EPYC 7R13 Processor cpu21@2649MHz",
|
870 |
+
"AMD EPYC 7R13 Processor cpu22@2649MHz",
|
871 |
+
"AMD EPYC 7R13 Processor cpu23@2673MHz",
|
872 |
+
"AMD EPYC 7R13 Processor cpu24@2649MHz",
|
873 |
+
"AMD EPYC 7R13 Processor cpu25@2649MHz",
|
874 |
+
"AMD EPYC 7R13 Processor cpu26@2649MHz",
|
875 |
+
"AMD EPYC 7R13 Processor cpu27@2649MHz",
|
876 |
+
"AMD EPYC 7R13 Processor cpu28@2649MHz",
|
877 |
+
"AMD EPYC 7R13 Processor cpu29@2649MHz",
|
878 |
+
"AMD EPYC 7R13 Processor cpu30@2673MHz",
|
879 |
+
"AMD EPYC 7R13 Processor cpu31@3391MHz",
|
880 |
+
"AMD EPYC 7R13 Processor cpu32@2649MHz",
|
881 |
+
"AMD EPYC 7R13 Processor cpu33@2649MHz",
|
882 |
+
"AMD EPYC 7R13 Processor cpu34@2649MHz",
|
883 |
+
"AMD EPYC 7R13 Processor cpu35@2649MHz",
|
884 |
+
"AMD EPYC 7R13 Processor cpu36@2649MHz",
|
885 |
+
"AMD EPYC 7R13 Processor cpu37@2649MHz",
|
886 |
+
"AMD EPYC 7R13 Processor cpu38@2649MHz",
|
887 |
+
"AMD EPYC 7R13 Processor cpu39@2673MHz",
|
888 |
+
"AMD EPYC 7R13 Processor cpu40@2649MHz",
|
889 |
+
"AMD EPYC 7R13 Processor cpu41@2673MHz",
|
890 |
+
"AMD EPYC 7R13 Processor cpu42@2673MHz",
|
891 |
+
"AMD EPYC 7R13 Processor cpu43@2673MHz",
|
892 |
+
"AMD EPYC 7R13 Processor cpu44@2673MHz",
|
893 |
+
"AMD EPYC 7R13 Processor cpu45@2673MHz",
|
894 |
+
"AMD EPYC 7R13 Processor cpu46@2673MHz",
|
895 |
+
"AMD EPYC 7R13 Processor cpu47@2649MHz",
|
896 |
+
"AMD EPYC 7R13 Processor cpu48@2649MHz",
|
897 |
+
"AMD EPYC 7R13 Processor cpu49@2649MHz",
|
898 |
+
"AMD EPYC 7R13 Processor cpu50@2649MHz",
|
899 |
+
"AMD EPYC 7R13 Processor cpu51@2649MHz",
|
900 |
+
"AMD EPYC 7R13 Processor cpu52@2649MHz",
|
901 |
+
"AMD EPYC 7R13 Processor cpu53@2649MHz",
|
902 |
+
"AMD EPYC 7R13 Processor cpu54@2673MHz",
|
903 |
+
"AMD EPYC 7R13 Processor cpu55@2673MHz",
|
904 |
+
"AMD EPYC 7R13 Processor cpu56@2673MHz",
|
905 |
+
"AMD EPYC 7R13 Processor cpu57@2649MHz",
|
906 |
+
"AMD EPYC 7R13 Processor cpu58@2649MHz",
|
907 |
+
"AMD EPYC 7R13 Processor cpu59@2649MHz",
|
908 |
+
"AMD EPYC 7R13 Processor cpu60@2673MHz",
|
909 |
+
"AMD EPYC 7R13 Processor cpu61@2649MHz",
|
910 |
+
"AMD EPYC 7R13 Processor cpu62@2649MHz",
|
911 |
+
"AMD EPYC 7R13 Processor cpu63@2649MHz",
|
912 |
+
"AMD EPYC 7R13 Processor cpu64@2649MHz",
|
913 |
+
"AMD EPYC 7R13 Processor cpu65@2649MHz",
|
914 |
+
"AMD EPYC 7R13 Processor cpu66@2649MHz",
|
915 |
+
"AMD EPYC 7R13 Processor cpu67@2649MHz",
|
916 |
+
"AMD EPYC 7R13 Processor cpu68@2649MHz",
|
917 |
+
"AMD EPYC 7R13 Processor cpu69@2649MHz",
|
918 |
+
"AMD EPYC 7R13 Processor cpu70@2649MHz",
|
919 |
+
"AMD EPYC 7R13 Processor cpu71@2649MHz",
|
920 |
+
"AMD EPYC 7R13 Processor cpu72@2649MHz",
|
921 |
+
"AMD EPYC 7R13 Processor cpu73@2649MHz",
|
922 |
+
"AMD EPYC 7R13 Processor cpu74@2649MHz",
|
923 |
+
"AMD EPYC 7R13 Processor cpu75@2649MHz",
|
924 |
+
"AMD EPYC 7R13 Processor cpu76@2649MHz",
|
925 |
+
"AMD EPYC 7R13 Processor cpu77@2649MHz",
|
926 |
+
"AMD EPYC 7R13 Processor cpu78@2649MHz",
|
927 |
+
"AMD EPYC 7R13 Processor cpu79@2649MHz",
|
928 |
+
"AMD EPYC 7R13 Processor cpu80@2649MHz",
|
929 |
+
"AMD EPYC 7R13 Processor cpu81@2649MHz",
|
930 |
+
"AMD EPYC 7R13 Processor cpu82@2649MHz",
|
931 |
+
"AMD EPYC 7R13 Processor cpu83@2649MHz",
|
932 |
+
"AMD EPYC 7R13 Processor cpu84@2673MHz",
|
933 |
+
"AMD EPYC 7R13 Processor cpu85@2673MHz",
|
934 |
+
"AMD EPYC 7R13 Processor cpu86@3111MHz",
|
935 |
+
"AMD EPYC 7R13 Processor cpu87@2649MHz",
|
936 |
+
"AMD EPYC 7R13 Processor cpu88@2649MHz",
|
937 |
+
"AMD EPYC 7R13 Processor cpu89@2649MHz",
|
938 |
+
"AMD EPYC 7R13 Processor cpu90@3111MHz",
|
939 |
+
"AMD EPYC 7R13 Processor cpu91@2649MHz",
|
940 |
+
"AMD EPYC 7R13 Processor cpu92@2649MHz",
|
941 |
+
"AMD EPYC 7R13 Processor cpu93@2649MHz",
|
942 |
+
"AMD EPYC 7R13 Processor cpu94@2649MHz",
|
943 |
+
"AMD EPYC 7R13 Processor cpu95@2649MHz"
|
944 |
+
],
|
945 |
+
"memory": "1999.99 GB",
|
946 |
+
"os_name": "Debian GNU/Linux",
|
947 |
+
"os_version": "11",
|
948 |
+
"kernel": "5.15.0-1048-aws",
|
949 |
+
"hostname": "ip-26-0-161-123"
|
950 |
+
}
|
951 |
+
}
|