Hugging Face's logo

Spaces:
textgeflecht
/
inference-benchmarking-results-phi4-8000-tokens
Sleeping

App Files Community
loghugging25 commited on
Commit
a391dfc
·
1 Parent(s): d1edcbb

update

Browse files
Files changed (1) hide show
  1. results/microsoft_phi-4_2025-05-21-22-54-55.json +296 -0
results/microsoft_phi-4_2025-05-21-22-54-55.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "max_vus": 800,
4
+ "duration_secs": 120,
5
+ "benchmark_kind": "Rate",
6
+ "warmup_duration_secs": 30,
7
+ "rates": [
8
+ 1.0,
9
+ 10.0,
10
+ 30.0,
11
+ 100.0
12
+ ],
13
+ "num_rates": 10,
14
+ "prompt_options": {
15
+ "num_tokens": 8000,
16
+ "min_tokens": 7980,
17
+ "max_tokens": 8020,
18
+ "variance": 10
19
+ },
20
+ "decode_options": {
21
+ "num_tokens": 8000,
22
+ "min_tokens": 7980,
23
+ "max_tokens": 8020,
24
+ "variance": 10
25
+ },
26
+ "tokenizer": "microsoft/phi-4",
27
+ "model_name": "phi-4",
28
+ "profile": null,
29
+ "meta": null,
30
+ "run_id": "LM Studio: lmstudio-community/phi-4-GGUF:Q8_0 (8000 tokens)"
31
+ },
32
+ "results": [
33
+ {
34
+ "id": "warmup",
35
+ "executor_type": "ConstantVUs",
36
+ "config": {
37
+ "max_vus": 1,
38
+ "duration_secs": 30,
39
+ "rate": null
40
+ },
41
+ "total_requests": 2,
42
+ "total_tokens": 1943,
43
+ "token_throughput_secs": 59.919314157710296,
44
+ "duration_ms": 32426,
45
+ "time_to_first_token_ms": {
46
+ "p50": 2134.585,
47
+ "p60": 2150.565,
48
+ "p70": 2166.545,
49
+ "p80": 2182.525,
50
+ "p90": 2198.505,
51
+ "p95": 2206.495,
52
+ "p99": 2212.887,
53
+ "avg": 2134.585
54
+ },
55
+ "inter_token_latency_ms": {
56
+ "p50": 14.48,
57
+ "p60": 14.502,
58
+ "p70": 14.524,
59
+ "p80": 14.546,
60
+ "p90": 14.568,
61
+ "p95": 14.579,
62
+ "p99": 14.588,
63
+ "avg": 14.48
64
+ },
65
+ "failed_requests": 0,
66
+ "successful_requests": 2,
67
+ "request_rate": 0.061677111845301384,
68
+ "total_tokens_sent": 16000,
69
+ "e2e_latency_ms": {
70
+ "p50": 16212.912,
71
+ "p60": 16862.646,
72
+ "p70": 17512.38,
73
+ "p80": 18162.114,
74
+ "p90": 18811.848,
75
+ "p95": 19136.715,
76
+ "p99": 19396.608,
77
+ "avg": 16212.912
78
+ }
79
+ },
80
+ {
81
+ "id": "[email protected]/s",
82
+ "executor_type": "ConstantArrivalRate",
83
+ "config": {
84
+ "max_vus": 800,
85
+ "duration_secs": 120,
86
+ "rate": 1.0
87
+ },
88
+ "total_requests": 8,
89
+ "total_tokens": 6498,
90
+ "token_throughput_secs": 58.88247207118268,
91
+ "duration_ms": 110355,
92
+ "time_to_first_token_ms": {
93
+ "p50": 46204.17,
94
+ "p60": 53006.013,
95
+ "p70": 62574.609,
96
+ "p80": 74984.604,
97
+ "p90": 84842.961,
98
+ "p95": 87755.337,
99
+ "p99": 90085.239,
100
+ "avg": 45669.215
101
+ },
102
+ "inter_token_latency_ms": {
103
+ "p50": 14.457,
104
+ "p60": 14.513,
105
+ "p70": 14.519,
106
+ "p80": 14.53,
107
+ "p90": 14.546,
108
+ "p95": 14.556,
109
+ "p99": 14.564,
110
+ "avg": 14.431
111
+ },
112
+ "failed_requests": 0,
113
+ "successful_requests": 8,
114
+ "request_rate": 0.07249304040773491,
115
+ "total_tokens_sent": 64000,
116
+ "e2e_latency_ms": {
117
+ "p50": 56016.808,
118
+ "p60": 66510.385,
119
+ "p70": 79438.235,
120
+ "p80": 86251.904,
121
+ "p90": 93700.73,
122
+ "p95": 98527.935,
123
+ "p99": 102389.699,
124
+ "avg": 57395.99
125
+ }
126
+ },
127
+ {
128
+ "id": "[email protected]/s",
129
+ "executor_type": "ConstantArrivalRate",
130
+ "config": {
131
+ "max_vus": 800,
132
+ "duration_secs": 120,
133
+ "rate": 10.0
134
+ },
135
+ "total_requests": 8,
136
+ "total_tokens": 6498,
137
+ "token_throughput_secs": 57.14855113119815,
138
+ "duration_ms": 113703,
139
+ "time_to_first_token_ms": {
140
+ "p50": 51652.607,
141
+ "p60": 59292.731,
142
+ "p70": 69739.148,
143
+ "p80": 83095.795,
144
+ "p90": 93805.033,
145
+ "p95": 97071.354,
146
+ "p99": 99684.411,
147
+ "avg": 51168.208
148
+ },
149
+ "inter_token_latency_ms": {
150
+ "p50": 14.668,
151
+ "p60": 14.747,
152
+ "p70": 14.777,
153
+ "p80": 14.792,
154
+ "p90": 14.822,
155
+ "p95": 14.851,
156
+ "p99": 14.874,
157
+ "avg": 14.664
158
+ },
159
+ "failed_requests": 0,
160
+ "successful_requests": 8,
161
+ "request_rate": 0.07035832703133044,
162
+ "total_tokens_sent": 64000,
163
+ "e2e_latency_ms": {
164
+ "p50": 61725.291,
165
+ "p60": 73154.943,
166
+ "p70": 87005.097,
167
+ "p80": 94591.843,
168
+ "p90": 102732.481,
169
+ "p95": 107867.995,
170
+ "p99": 111976.407,
171
+ "avg": 63089.952
172
+ }
173
+ },
174
+ {
175
+ "id": "[email protected]/s",
176
+ "executor_type": "ConstantArrivalRate",
177
+ "config": {
178
+ "max_vus": 800,
179
+ "duration_secs": 120,
180
+ "rate": 30.0
181
+ },
182
+ "total_requests": 7,
183
+ "total_tokens": 6000,
184
+ "token_throughput_secs": 58.64714193076017,
185
+ "duration_ms": 102306,
186
+ "time_to_first_token_ms": {
187
+ "p50": 45581.154,
188
+ "p60": 54463.137,
189
+ "p70": 64301.527,
190
+ "p80": 76052.732,
191
+ "p90": 83687.32,
192
+ "p95": 86475.459,
193
+ "p99": 88705.971,
194
+ "avg": 47182.711
195
+ },
196
+ "inter_token_latency_ms": {
197
+ "p50": 14.569,
198
+ "p60": 14.638,
199
+ "p70": 14.694,
200
+ "p80": 14.727,
201
+ "p90": 14.74,
202
+ "p95": 14.743,
203
+ "p99": 14.744,
204
+ "avg": 14.61
205
+ },
206
+ "failed_requests": 0,
207
+ "successful_requests": 7,
208
+ "request_rate": 0.06842166558588686,
209
+ "total_tokens_sent": 56000,
210
+ "e2e_latency_ms": {
211
+ "p50": 58271.561,
212
+ "p60": 70050.39,
213
+ "p70": 79759.973,
214
+ "p80": 85331.066,
215
+ "p90": 93155.555,
216
+ "p95": 97631.149,
217
+ "p99": 101211.625,
218
+ "avg": 59689.317
219
+ }
220
+ },
221
+ {
222
+ "id": "[email protected]/s",
223
+ "executor_type": "ConstantArrivalRate",
224
+ "config": {
225
+ "max_vus": 800,
226
+ "duration_secs": 120,
227
+ "rate": 100.0
228
+ },
229
+ "total_requests": 7,
230
+ "total_tokens": 6000,
231
+ "token_throughput_secs": 59.165538126280964,
232
+ "duration_ms": 101410,
233
+ "time_to_first_token_ms": {
234
+ "p50": 45445.441,
235
+ "p60": 54349.382,
236
+ "p70": 64163.525,
237
+ "p80": 75798.072,
238
+ "p90": 83342.879,
239
+ "p95": 86092.848,
240
+ "p99": 88292.823,
241
+ "avg": 47057.018
242
+ },
243
+ "inter_token_latency_ms": {
244
+ "p50": 14.418,
245
+ "p60": 14.464,
246
+ "p70": 14.495,
247
+ "p80": 14.495,
248
+ "p90": 14.532,
249
+ "p95": 14.559,
250
+ "p99": 14.581,
251
+ "avg": 14.434
252
+ },
253
+ "failed_requests": 0,
254
+ "successful_requests": 7,
255
+ "request_rate": 0.06902646114732779,
256
+ "total_tokens_sent": 56000,
257
+ "e2e_latency_ms": {
258
+ "p50": 58150.729,
259
+ "p60": 69807.518,
260
+ "p70": 79415.902,
261
+ "p80": 84927.475,
262
+ "p90": 92602.399,
263
+ "p95": 96980.699,
264
+ "p99": 100483.34,
265
+ "avg": 59427.632
266
+ }
267
+ }
268
+ ],
269
+ "start_time": "2025-05-21T22:39:51.750052507+00:00",
270
+ "end_time": "2025-05-21T22:54:55.393146913+00:00",
271
+ "system": {
272
+ "cpu": [
273
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu0@4699MHz",
274
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu1@4699MHz",
275
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu2@4699MHz",
276
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu3@4699MHz",
277
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu4@4699MHz",
278
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu5@4699MHz",
279
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu6@4699MHz",
280
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu7@4699MHz",
281
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu8@4699MHz",
282
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu9@4699MHz",
283
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu10@4699MHz",
284
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu11@4699MHz",
285
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu12@4699MHz",
286
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu13@4699MHz",
287
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu14@4699MHz",
288
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu15@4699MHz"
289
+ ],
290
+ "memory": "83.47 GB",
291
+ "os_name": "Debian GNU/Linux",
292
+ "os_version": "11",
293
+ "kernel": "5.15.167.4-microsoft-standard-WSL2",
294
+ "hostname": "computer"
295
+ }
296
+ }