Hugging Face's logo

Spaces:
textgeflecht
/
inference-benchmarking-results-phi4-200-tokens
Running

App Files Community
textgeflecht commited on
Commit
4020622
·
verified ·
1 Parent(s): f0d353c

Upload microsoft_phi-4_2025-05-27-08-26-44.json

Browse files
Files changed (1) hide show
  1. results/microsoft_phi-4_2025-05-27-08-26-44.json +296 -0
results/microsoft_phi-4_2025-05-27-08-26-44.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": 200,
16
+ "min_tokens": 180,
17
+ "max_tokens": 220,
18
+ "variance": 10
19
+ },
20
+ "decode_options": {
21
+ "num_tokens": 200,
22
+ "min_tokens": 180,
23
+ "max_tokens": 220,
24
+ "variance": 10
25
+ },
26
+ "tokenizer": "microsoft/phi-4",
27
+ "model_name": "phi-4",
28
+ "profile": null,
29
+ "meta": null,
30
+ "run_id": "llama.cpp -np 64 -fa: unsloth/phi-4-GGUF:Q8_0 (200 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": 14,
42
+ "total_tokens": 2616,
43
+ "token_throughput_secs": 82.09737197039337,
44
+ "duration_ms": 31864,
45
+ "time_to_first_token_ms": {
46
+ "p50": 44.212,
47
+ "p60": 44.43,
48
+ "p70": 44.447,
49
+ "p80": 44.685,
50
+ "p90": 46.689,
51
+ "p95": 101.515,
52
+ "p99": 166.751,
53
+ "avg": 54.814
54
+ },
55
+ "inter_token_latency_ms": {
56
+ "p50": 11.936,
57
+ "p60": 11.949,
58
+ "p70": 11.99,
59
+ "p80": 12.026,
60
+ "p90": 12.063,
61
+ "p95": 12.084,
62
+ "p99": 12.101,
63
+ "avg": 11.966
64
+ },
65
+ "failed_requests": 1,
66
+ "successful_requests": 13,
67
+ "request_rate": 0.4079762368559304,
68
+ "total_tokens_sent": 2600,
69
+ "e2e_latency_ms": {
70
+ "p50": 2456.559,
71
+ "p60": 2469.389,
72
+ "p70": 2493.285,
73
+ "p80": 2535.156,
74
+ "p90": 2552.768,
75
+ "p95": 2587.735,
76
+ "p99": 2628.358,
77
+ "avg": 2450.946
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": 115,
89
+ "total_tokens": 22501,
90
+ "token_throughput_secs": 192.37062312112172,
91
+ "duration_ms": 116966,
92
+ "time_to_first_token_ms": {
93
+ "p50": 61.967,
94
+ "p60": 64.023,
95
+ "p70": 67.891,
96
+ "p80": 70.615,
97
+ "p90": 179.67,
98
+ "p95": 249.752,
99
+ "p99": 280.615,
100
+ "avg": 82.253
101
+ },
102
+ "inter_token_latency_ms": {
103
+ "p50": 21.568,
104
+ "p60": 21.986,
105
+ "p70": 22.5,
106
+ "p80": 24.021,
107
+ "p90": 24.927,
108
+ "p95": 25.173,
109
+ "p99": 25.5,
110
+ "avg": 21.6
111
+ },
112
+ "failed_requests": 0,
113
+ "successful_requests": 115,
114
+ "request_rate": 0.9831839322220789,
115
+ "total_tokens_sent": 23000,
116
+ "e2e_latency_ms": {
117
+ "p50": 4375.586,
118
+ "p60": 4490.126,
119
+ "p70": 4621.206,
120
+ "p80": 4823.308,
121
+ "p90": 4978.692,
122
+ "p95": 5127.569,
123
+ "p99": 5356.264,
124
+ "avg": 4287.312
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": 291,
136
+ "total_tokens": 55230,
137
+ "token_throughput_secs": 476.1656111230306,
138
+ "duration_ms": 115989,
139
+ "time_to_first_token_ms": {
140
+ "p50": 27742.426,
141
+ "p60": 30089.886,
142
+ "p70": 39910.2,
143
+ "p80": 49196.882,
144
+ "p90": 55356.185,
145
+ "p95": 61600.512,
146
+ "p99": 65840.776,
147
+ "avg": 26521.135
148
+ },
149
+ "inter_token_latency_ms": {
150
+ "p50": 123.965,
151
+ "p60": 126.573,
152
+ "p70": 129.489,
153
+ "p80": 131.7,
154
+ "p90": 134.469,
155
+ "p95": 137.356,
156
+ "p99": 162.616,
157
+ "avg": 119.313
158
+ },
159
+ "failed_requests": 1,
160
+ "successful_requests": 290,
161
+ "request_rate": 2.500235872273744,
162
+ "total_tokens_sent": 58000,
163
+ "e2e_latency_ms": {
164
+ "p50": 49879.178,
165
+ "p60": 56462.363,
166
+ "p70": 64173.1,
167
+ "p80": 73704.057,
168
+ "p90": 79973.489,
169
+ "p95": 86852.409,
170
+ "p99": 91155.634,
171
+ "avg": 49055.768
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": 312,
183
+ "total_tokens": 51846,
184
+ "token_throughput_secs": 434.8417386944988,
185
+ "duration_ms": 119229,
186
+ "time_to_first_token_ms": {
187
+ "p50": 32390.361,
188
+ "p60": 42662.793,
189
+ "p70": 47412.886,
190
+ "p80": 64582.739,
191
+ "p90": 70287.382,
192
+ "p95": 75253.178,
193
+ "p99": 88837.511,
194
+ "avg": 34677.416
195
+ },
196
+ "inter_token_latency_ms": {
197
+ "p50": 132.881,
198
+ "p60": 134.588,
199
+ "p70": 136.483,
200
+ "p80": 140.498,
201
+ "p90": 181.373,
202
+ "p95": 264.941,
203
+ "p99": 359.947,
204
+ "avg": 142.854
205
+ },
206
+ "failed_requests": 1,
207
+ "successful_requests": 311,
208
+ "request_rate": 2.608413006480522,
209
+ "total_tokens_sent": 62200,
210
+ "e2e_latency_ms": {
211
+ "p50": 51189.866,
212
+ "p60": 66664.912,
213
+ "p70": 72786.556,
214
+ "p80": 88077.779,
215
+ "p90": 96316.319,
216
+ "p95": 100535.272,
217
+ "p99": 107976.58,
218
+ "avg": 55471.611
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": 223,
230
+ "total_tokens": 41363,
231
+ "token_throughput_secs": 346.1455627522371,
232
+ "duration_ms": 119495,
233
+ "time_to_first_token_ms": {
234
+ "p50": 44275.778,
235
+ "p60": 55017.559,
236
+ "p70": 61284.522,
237
+ "p80": 71772.949,
238
+ "p90": 81258.892,
239
+ "p95": 85319.529,
240
+ "p99": 90189.098,
241
+ "avg": 45209.255
242
+ },
243
+ "inter_token_latency_ms": {
244
+ "p50": 141.155,
245
+ "p60": 143.438,
246
+ "p70": 145.612,
247
+ "p80": 148.448,
248
+ "p90": 152.661,
249
+ "p95": 154.2,
250
+ "p99": 236.805,
251
+ "avg": 142.661
252
+ },
253
+ "failed_requests": 5,
254
+ "successful_requests": 218,
255
+ "request_rate": 1.8243292962306334,
256
+ "total_tokens_sent": 43600,
257
+ "e2e_latency_ms": {
258
+ "p50": 72222.073,
259
+ "p60": 81429.587,
260
+ "p70": 89429.26,
261
+ "p80": 100108.754,
262
+ "p90": 109091.856,
263
+ "p95": 114918.64,
264
+ "p99": 117293.588,
265
+ "avg": 72031.422
266
+ }
267
+ }
268
+ ],
269
+ "start_time": "2025-05-27T08:12:54.195804371+00:00",
270
+ "end_time": "2025-05-27T08:26:44.706549601+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
+ }