Upload /gemma-7b/int8_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json with huggingface_hub
Browse files
gemma-7b/int8_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json
CHANGED
@@ -2,194 +2,190 @@
|
|
2 |
"prefill": {
|
3 |
"memory": {
|
4 |
"unit": "MB",
|
5 |
-
"max_ram":
|
6 |
"max_vram": 10504.634368,
|
7 |
"max_reserved": 10011.803648,
|
8 |
"max_allocated": 9921.83552
|
9 |
},
|
10 |
"latency": {
|
11 |
"unit": "s",
|
12 |
-
"mean": 0.
|
13 |
-
"stdev": 0.
|
14 |
"values": [
|
15 |
-
0.
|
16 |
-
0.
|
17 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
0.05911040115356445,
|
19 |
-
0.
|
20 |
-
0.
|
21 |
-
0.
|
22 |
-
0.
|
23 |
-
0.
|
24 |
-
0.
|
25 |
-
0.
|
26 |
-
0.
|
27 |
-
0.
|
28 |
-
0.
|
29 |
-
0.
|
30 |
-
0.
|
31 |
-
0.
|
32 |
-
0.
|
33 |
-
0.
|
34 |
-
0.
|
35 |
-
0.
|
36 |
-
0.
|
37 |
-
0.
|
38 |
-
0.
|
39 |
-
0.
|
40 |
-
0.
|
41 |
-
0.
|
42 |
-
0.
|
43 |
-
0.
|
44 |
-
0.
|
45 |
-
0.
|
46 |
-
0.
|
47 |
-
0.
|
48 |
-
0.
|
49 |
-
0.
|
50 |
-
0.
|
51 |
-
0.
|
52 |
-
0.
|
53 |
-
0.
|
54 |
-
0.
|
55 |
-
0.
|
56 |
-
0.
|
57 |
-
0.
|
58 |
-
0.
|
59 |
-
0.
|
60 |
-
0.
|
61 |
-
0.
|
62 |
-
0.
|
63 |
-
0.
|
64 |
-
0.
|
65 |
-
0.
|
66 |
-
0.
|
67 |
-
0.
|
68 |
-
0.
|
69 |
-
0.
|
70 |
-
0.
|
71 |
-
0.
|
72 |
-
0.
|
73 |
-
0.
|
74 |
-
0.
|
75 |
-
0.
|
76 |
-
0.
|
77 |
-
0.
|
78 |
-
0.
|
79 |
-
0.
|
80 |
-
0.
|
81 |
-
0.
|
82 |
-
0.
|
83 |
-
0.
|
84 |
-
0.
|
85 |
-
0.
|
86 |
-
0.
|
87 |
-
0.
|
88 |
-
0.
|
89 |
-
0.
|
90 |
-
0.
|
91 |
-
0.
|
92 |
-
0.
|
93 |
-
0.0579051513671875,
|
94 |
-
0.05801369476318359,
|
95 |
-
0.057988094329833983,
|
96 |
-
0.05773516845703125,
|
97 |
-
0.05791641616821289,
|
98 |
-
0.05794508743286133,
|
99 |
-
0.058033153533935546,
|
100 |
-
0.05788467025756836,
|
101 |
-
0.05802700805664063,
|
102 |
-
0.05804851150512695,
|
103 |
-
0.05807308959960938,
|
104 |
-
0.05795328140258789,
|
105 |
-
0.05804851150512695,
|
106 |
-
0.05790719985961914,
|
107 |
-
0.05848883056640625,
|
108 |
-
0.05825331115722656,
|
109 |
-
0.05809766387939453,
|
110 |
-
0.058039295196533204,
|
111 |
-
0.058180606842041016,
|
112 |
-
0.05796147155761719,
|
113 |
-
0.058068992614746094,
|
114 |
-
0.05791641616821289,
|
115 |
-
0.058449920654296876,
|
116 |
-
0.05794508743286133,
|
117 |
-
0.05796966552734375,
|
118 |
-
0.05796147155761719,
|
119 |
-
0.05791129684448242,
|
120 |
-
0.057845760345458984,
|
121 |
-
0.058014720916748044,
|
122 |
-
0.058038272857666016,
|
123 |
-
0.058028064727783206,
|
124 |
-
0.058031105041503904,
|
125 |
-
0.058057727813720705,
|
126 |
-
0.057929729461669924,
|
127 |
-
0.05796352005004883,
|
128 |
-
0.05790316772460938,
|
129 |
-
0.058003456115722656,
|
130 |
-
0.057826305389404295,
|
131 |
-
0.05790105438232422,
|
132 |
-
0.05791129684448242,
|
133 |
-
0.058126335144042966,
|
134 |
-
0.05795840072631836,
|
135 |
-
0.05795430374145508,
|
136 |
-
0.05791129684448242,
|
137 |
-
0.05808127975463867,
|
138 |
-
0.05797478485107422,
|
139 |
-
0.058065921783447265,
|
140 |
-
0.05798204803466797,
|
141 |
-
0.058071041107177736,
|
142 |
-
0.058194942474365234,
|
143 |
-
0.05803212738037109,
|
144 |
-
0.057957374572753906,
|
145 |
-
0.05815193557739258,
|
146 |
-
0.05793382263183594,
|
147 |
-
0.057883647918701174,
|
148 |
-
0.05798912048339844,
|
149 |
-
0.06166425704956055,
|
150 |
-
0.05828812789916992,
|
151 |
-
0.05791455841064453,
|
152 |
-
0.057929729461669924,
|
153 |
-
0.05821747207641602,
|
154 |
-
0.05783244705200195,
|
155 |
-
0.05806489562988281,
|
156 |
-
0.058017791748046874,
|
157 |
-
0.0581396484375,
|
158 |
-
0.058031105041503904,
|
159 |
-
0.05799731063842774,
|
160 |
-
0.05790617752075195,
|
161 |
-
0.0581058578491211,
|
162 |
-
0.058074111938476565,
|
163 |
-
0.05796761703491211,
|
164 |
-
0.05783859252929688,
|
165 |
-
0.05787443161010742,
|
166 |
-
0.05796352005004883,
|
167 |
-
0.058074111938476565,
|
168 |
-
0.05798400115966797,
|
169 |
-
0.05815398406982422,
|
170 |
-
0.057793792724609376,
|
171 |
-
0.05800147247314453,
|
172 |
-
0.057919486999511716,
|
173 |
-
0.058019840240478515,
|
174 |
-
0.058022911071777344,
|
175 |
-
0.05803724670410156,
|
176 |
-
0.058120193481445315,
|
177 |
-
0.05827174377441406,
|
178 |
-
0.05803417587280273,
|
179 |
-
0.05795635223388672,
|
180 |
-
0.05810073471069336,
|
181 |
-
0.058019840240478515,
|
182 |
-
0.05797580718994141,
|
183 |
-
0.05812736129760742,
|
184 |
-
0.05790822219848633,
|
185 |
-
0.058484832763671876,
|
186 |
-
0.058049537658691405,
|
187 |
-
0.05807206344604492
|
188 |
]
|
189 |
},
|
190 |
"throughput": {
|
191 |
"unit": "tokens/s",
|
192 |
-
"value":
|
193 |
},
|
194 |
"energy": null,
|
195 |
"efficiency": null
|
@@ -197,22 +193,22 @@
|
|
197 |
"decode": {
|
198 |
"memory": {
|
199 |
"unit": "MB",
|
200 |
-
"max_ram":
|
201 |
"max_vram": 10892.607488,
|
202 |
"max_reserved": 10399.776768,
|
203 |
"max_allocated": 10301.4272
|
204 |
},
|
205 |
"latency": {
|
206 |
"unit": "s",
|
207 |
-
"mean": 14.
|
208 |
"stdev": 0,
|
209 |
"values": [
|
210 |
-
14.
|
211 |
]
|
212 |
},
|
213 |
"throughput": {
|
214 |
"unit": "tokens/s",
|
215 |
-
"value": 17.
|
216 |
},
|
217 |
"energy": null,
|
218 |
"efficiency": null
|
@@ -221,269 +217,269 @@
|
|
221 |
"memory": null,
|
222 |
"latency": {
|
223 |
"unit": "s",
|
224 |
-
"mean": 0.
|
225 |
-
"stdev": 0.
|
226 |
"values": [
|
227 |
-
0.
|
228 |
-
0.
|
229 |
-
0.
|
230 |
-
0.
|
231 |
-
0.
|
232 |
-
0.
|
233 |
-
0.
|
234 |
-
0.
|
235 |
-
0.
|
236 |
-
0.
|
237 |
-
0.
|
238 |
-
0.
|
239 |
-
0.
|
240 |
-
0.
|
241 |
-
0.
|
242 |
-
0.
|
243 |
-
0.
|
244 |
-
0.
|
245 |
-
0.
|
246 |
-
0.
|
247 |
-
0.
|
248 |
-
0.
|
249 |
-
0.
|
250 |
-
0.
|
251 |
-
0.
|
252 |
-
0.
|
253 |
-
0.
|
254 |
-
0.
|
255 |
-
0.
|
256 |
-
0.
|
257 |
-
0.
|
258 |
-
0.
|
259 |
-
0.
|
260 |
-
0.
|
261 |
-
0.
|
262 |
-
0.
|
263 |
-
0.
|
264 |
-
0.
|
265 |
-
0.
|
266 |
-
0.
|
267 |
-
0.
|
268 |
-
0.
|
269 |
-
0.
|
270 |
-
0.
|
271 |
-
0.
|
272 |
-
0.
|
273 |
-
0.
|
274 |
-
0.
|
275 |
-
0.
|
276 |
-
0.
|
277 |
-
0.
|
278 |
-
0.
|
279 |
-
0.
|
280 |
-
0.
|
281 |
-
0.
|
282 |
-
0.
|
283 |
-
0.
|
284 |
-
0.
|
285 |
-
0.
|
286 |
-
0.
|
287 |
-
0.
|
288 |
-
0.
|
289 |
-
0.
|
290 |
-
0.
|
291 |
-
0.
|
292 |
-
0.
|
293 |
-
0.
|
294 |
-
0.
|
295 |
-
0.
|
296 |
-
0.
|
297 |
-
0.
|
298 |
-
0.
|
299 |
-
0.
|
300 |
-
0.
|
301 |
-
0.
|
302 |
-
0.
|
303 |
-
0.
|
304 |
-
0.
|
305 |
-
0.
|
306 |
-
0.
|
307 |
-
0.
|
308 |
-
0.
|
309 |
-
0.
|
310 |
-
0.
|
311 |
-
0.
|
312 |
-
0.
|
313 |
-
0.
|
314 |
-
0.
|
315 |
-
0.
|
316 |
-
0.
|
317 |
-
0.
|
318 |
-
0.
|
319 |
-
0.
|
320 |
-
0.
|
321 |
-
0.
|
322 |
-
0.
|
323 |
-
0.
|
324 |
-
0.
|
325 |
-
0.
|
326 |
-
0.
|
327 |
-
0.
|
328 |
-
0.
|
329 |
-
0.
|
330 |
-
0.
|
331 |
-
0.
|
332 |
-
0.
|
333 |
-
0.
|
334 |
-
0.
|
335 |
-
0.
|
336 |
-
0.
|
337 |
-
0.
|
338 |
-
0.05730112075805664,
|
339 |
-
0.05706124877929687,
|
340 |
-
0.05709107208251953,
|
341 |
-
0.057262081146240235,
|
342 |
-
0.057188350677490236,
|
343 |
-
0.05717196655273438,
|
344 |
-
0.057164798736572264,
|
345 |
-
0.05718425750732422,
|
346 |
-
0.05717196655273438,
|
347 |
-
0.05717094421386719,
|
348 |
-
0.05815628814697266,
|
349 |
-
0.05723827362060547,
|
350 |
-
0.0572119026184082,
|
351 |
-
0.057106433868408205,
|
352 |
-
0.05715865707397461,
|
353 |
-
0.05717708969116211,
|
354 |
-
0.05728768157958984,
|
355 |
0.05785804748535156,
|
356 |
-
0.
|
357 |
-
0.
|
358 |
-
0.
|
359 |
-
0.
|
360 |
-
0.
|
361 |
-
0.
|
362 |
-
0.
|
363 |
-
0.
|
364 |
-
0.
|
365 |
-
0.
|
366 |
-
0.
|
367 |
-
0.
|
368 |
-
0.
|
369 |
-
0.
|
370 |
-
0.
|
371 |
-
0.
|
372 |
-
0.
|
373 |
-
0.
|
374 |
-
0.
|
375 |
-
0.
|
376 |
-
0.
|
377 |
-
0.
|
378 |
-
0.
|
379 |
-
0.
|
380 |
-
0.
|
381 |
-
0.
|
382 |
-
0.
|
383 |
-
0.
|
384 |
-
0.
|
385 |
-
0.
|
386 |
-
0.
|
387 |
-
0.
|
388 |
-
0.
|
389 |
-
0.
|
390 |
-
0.
|
391 |
-
0.
|
392 |
-
0.
|
393 |
-
0.
|
394 |
-
0.
|
395 |
-
0.
|
396 |
-
0.
|
397 |
-
0.
|
398 |
-
0.
|
399 |
-
0.
|
400 |
-
0.
|
401 |
-
0.
|
402 |
-
0.
|
403 |
-
0.
|
404 |
-
0.
|
405 |
-
0.
|
406 |
-
0.
|
407 |
-
0.
|
408 |
-
0.
|
409 |
-
0.
|
410 |
-
0.
|
411 |
-
0.
|
412 |
-
0.
|
413 |
-
0.
|
414 |
-
0.
|
415 |
-
0.
|
416 |
-
0.
|
417 |
-
0.
|
418 |
-
0.
|
419 |
-
0.
|
420 |
-
0.
|
421 |
-
0.
|
422 |
-
0.
|
423 |
-
0.
|
424 |
-
0.
|
425 |
-
0.
|
426 |
-
0.
|
427 |
-
0.
|
428 |
-
0.
|
429 |
-
0.
|
430 |
-
0.
|
431 |
-
0.
|
432 |
-
0.
|
433 |
-
0.
|
434 |
-
0.
|
435 |
-
0.
|
436 |
-
0.
|
437 |
-
0.
|
438 |
-
0.
|
439 |
-
0.
|
440 |
-
0.
|
441 |
-
0.
|
442 |
-
0.
|
443 |
-
0.
|
444 |
-
0.
|
445 |
-
0.
|
446 |
-
0.
|
447 |
-
0.
|
448 |
-
0.
|
449 |
-
0.
|
450 |
-
0.
|
451 |
-
0.
|
452 |
-
0.
|
453 |
-
0.
|
454 |
-
0.
|
455 |
-
0.
|
456 |
-
0.
|
457 |
-
0.
|
458 |
-
0.
|
459 |
-
0.
|
460 |
-
0.
|
461 |
-
0.
|
462 |
-
0.
|
463 |
-
0.
|
464 |
-
0.
|
465 |
-
0.
|
466 |
-
0.
|
467 |
-
0.
|
468 |
-
0.
|
469 |
-
0.
|
470 |
-
0.
|
471 |
-
0.
|
472 |
-
0.
|
473 |
-
0.
|
474 |
-
0.
|
475 |
-
0.
|
476 |
-
0.
|
477 |
-
0.
|
478 |
-
0.
|
479 |
-
0.
|
480 |
-
0.
|
481 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
482 |
]
|
483 |
},
|
484 |
"throughput": {
|
485 |
"unit": "tokens/s",
|
486 |
-
"value": 17.
|
487 |
},
|
488 |
"energy": null,
|
489 |
"efficiency": null
|
|
|
2 |
"prefill": {
|
3 |
"memory": {
|
4 |
"unit": "MB",
|
5 |
+
"max_ram": 4575.711232,
|
6 |
"max_vram": 10504.634368,
|
7 |
"max_reserved": 10011.803648,
|
8 |
"max_allocated": 9921.83552
|
9 |
},
|
10 |
"latency": {
|
11 |
"unit": "s",
|
12 |
+
"mean": 0.05921143521641836,
|
13 |
+
"stdev": 0.000792575270597166,
|
14 |
"values": [
|
15 |
+
0.06676448059082031,
|
16 |
+
0.06044364929199219,
|
17 |
+
0.06004326248168945,
|
18 |
+
0.06046310424804688,
|
19 |
+
0.061454334259033204,
|
20 |
+
0.06348697662353515,
|
21 |
+
0.06285107040405273,
|
22 |
+
0.05910425567626953,
|
23 |
+
0.059529216766357425,
|
24 |
+
0.058993663787841794,
|
25 |
+
0.05899161529541016,
|
26 |
+
0.058992641448974606,
|
27 |
+
0.05882572937011719,
|
28 |
+
0.05901311874389648,
|
29 |
+
0.05894041442871094,
|
30 |
+
0.05910323333740235,
|
31 |
+
0.059481086730957033,
|
32 |
+
0.059025409698486325,
|
33 |
+
0.05894041442871094,
|
34 |
+
0.05875302505493164,
|
35 |
+
0.058946559906005856,
|
36 |
+
0.058992641448974606,
|
37 |
+
0.05883084869384766,
|
38 |
+
0.058790912628173826,
|
39 |
+
0.05885235214233398,
|
40 |
+
0.0587325439453125,
|
41 |
+
0.05886259078979492,
|
42 |
+
0.05886054229736328,
|
43 |
+
0.05898342514038086,
|
44 |
+
0.059101184844970706,
|
45 |
+
0.059009025573730466,
|
46 |
+
0.05897727966308594,
|
47 |
+
0.05902131271362305,
|
48 |
+
0.05902336120605469,
|
49 |
+
0.05903769683837891,
|
50 |
+
0.05900697708129883,
|
51 |
+
0.05892403030395508,
|
52 |
+
0.05884723281860352,
|
53 |
+
0.0589219856262207,
|
54 |
+
0.058893310546875,
|
55 |
+
0.05906227111816406,
|
56 |
+
0.058967041015625,
|
57 |
+
0.059650047302246094,
|
58 |
+
0.05895065689086914,
|
59 |
+
0.05893017578125,
|
60 |
+
0.05893529510498047,
|
61 |
+
0.05890867233276367,
|
62 |
+
0.05906022262573242,
|
63 |
+
0.05902950286865234,
|
64 |
+
0.05907660675048828,
|
65 |
+
0.0593438720703125,
|
66 |
+
0.058823680877685545,
|
67 |
+
0.05882265472412109,
|
68 |
+
0.058834945678710934,
|
69 |
+
0.05902950286865234,
|
70 |
+
0.05893017578125,
|
71 |
+
0.05893427276611328,
|
72 |
+
0.05901004791259765,
|
73 |
+
0.05907046508789063,
|
74 |
+
0.059068416595458986,
|
75 |
+
0.05898956680297852,
|
76 |
+
0.05886057662963867,
|
77 |
+
0.058897407531738284,
|
78 |
+
0.058889217376708984,
|
79 |
+
0.05896499252319336,
|
80 |
+
0.05895577621459961,
|
81 |
+
0.0591278076171875,
|
82 |
+
0.05889023971557617,
|
83 |
+
0.05895884704589844,
|
84 |
+
0.058931198120117184,
|
85 |
+
0.05883699035644531,
|
86 |
+
0.05898758316040039,
|
87 |
+
0.05896806335449219,
|
88 |
+
0.0588144645690918,
|
89 |
+
0.058859519958496094,
|
90 |
+
0.05893529510498047,
|
91 |
+
0.059394046783447264,
|
92 |
+
0.05888409423828125,
|
93 |
+
0.05885955047607422,
|
94 |
+
0.05888000106811524,
|
95 |
+
0.05881753540039063,
|
96 |
+
0.058875904083251954,
|
97 |
+
0.05895577621459961,
|
98 |
+
0.05883084869384766,
|
99 |
+
0.05939302444458008,
|
100 |
+
0.05904793548583984,
|
101 |
+
0.058946559906005856,
|
102 |
+
0.05897225570678711,
|
103 |
+
0.058875904083251954,
|
104 |
+
0.05888307189941406,
|
105 |
+
0.05883903884887695,
|
106 |
+
0.05902643203735351,
|
107 |
+
0.05912063980102539,
|
108 |
+
0.059084800720214846,
|
109 |
0.05911040115356445,
|
110 |
+
0.059202560424804686,
|
111 |
+
0.059167743682861325,
|
112 |
+
0.059079681396484375,
|
113 |
+
0.0592097282409668,
|
114 |
+
0.059000831604003906,
|
115 |
+
0.05905203247070313,
|
116 |
+
0.05910528182983398,
|
117 |
+
0.05903769683837891,
|
118 |
+
0.058995712280273435,
|
119 |
+
0.059224063873291016,
|
120 |
+
0.05920665740966797,
|
121 |
+
0.05917695999145508,
|
122 |
+
0.05895167922973633,
|
123 |
+
0.05926604843139648,
|
124 |
+
0.05922918319702149,
|
125 |
+
0.059701248168945314,
|
126 |
+
0.059235328674316405,
|
127 |
+
0.05928979110717773,
|
128 |
+
0.05924863815307617,
|
129 |
+
0.059238399505615234,
|
130 |
+
0.05924256134033203,
|
131 |
+
0.059227134704589846,
|
132 |
+
0.05909503936767578,
|
133 |
+
0.05974528121948242,
|
134 |
+
0.059104351043701174,
|
135 |
+
0.05924761581420898,
|
136 |
+
0.05929676818847656,
|
137 |
+
0.059256832122802736,
|
138 |
+
0.0592803840637207,
|
139 |
+
0.05923231887817383,
|
140 |
+
0.0592803840637207,
|
141 |
+
0.0592803840637207,
|
142 |
+
0.059324417114257816,
|
143 |
+
0.05926092910766602,
|
144 |
+
0.05919539260864258,
|
145 |
+
0.05927833557128906,
|
146 |
+
0.05923737716674805,
|
147 |
+
0.05921484756469726,
|
148 |
+
0.05929369735717773,
|
149 |
+
0.05917900848388672,
|
150 |
+
0.05922304153442383,
|
151 |
+
0.05935308837890625,
|
152 |
+
0.05933977508544922,
|
153 |
+
0.05925888061523438,
|
154 |
+
0.05911040115356445,
|
155 |
+
0.059015167236328124,
|
156 |
+
0.05928857421875,
|
157 |
+
0.05907763290405273,
|
158 |
+
0.059302913665771485,
|
159 |
+
0.0597628173828125,
|
160 |
+
0.059238399505615234,
|
161 |
+
0.05927231979370117,
|
162 |
+
0.059262977600097654,
|
163 |
+
0.05916262435913086,
|
164 |
+
0.05918003082275391,
|
165 |
+
0.059232257843017576,
|
166 |
+
0.05911859130859375,
|
167 |
+
0.059646976470947265,
|
168 |
+
0.05907660675048828,
|
169 |
+
0.059014144897460936,
|
170 |
+
0.05913087844848633,
|
171 |
+
0.059150337219238285,
|
172 |
+
0.05915852737426758,
|
173 |
+
0.059028480529785154,
|
174 |
+
0.058916862487792966,
|
175 |
+
0.0590552978515625,
|
176 |
+
0.05906739044189453,
|
177 |
+
0.059084800720214846,
|
178 |
+
0.059041793823242185,
|
179 |
+
0.059066368103027345,
|
180 |
+
0.05911040115356445,
|
181 |
+
0.05908889770507812,
|
182 |
+
0.05897318267822266,
|
183 |
+
0.059109375
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
184 |
]
|
185 |
},
|
186 |
"throughput": {
|
187 |
"unit": "tokens/s",
|
188 |
+
"value": 4323.489188605504
|
189 |
},
|
190 |
"energy": null,
|
191 |
"efficiency": null
|
|
|
193 |
"decode": {
|
194 |
"memory": {
|
195 |
"unit": "MB",
|
196 |
+
"max_ram": 4575.711232,
|
197 |
"max_vram": 10892.607488,
|
198 |
"max_reserved": 10399.776768,
|
199 |
"max_allocated": 10301.4272
|
200 |
},
|
201 |
"latency": {
|
202 |
"unit": "s",
|
203 |
+
"mean": 14.784453826904297,
|
204 |
"stdev": 0,
|
205 |
"values": [
|
206 |
+
14.784453826904297
|
207 |
]
|
208 |
},
|
209 |
"throughput": {
|
210 |
"unit": "tokens/s",
|
211 |
+
"value": 17.247847163346595
|
212 |
},
|
213 |
"energy": null,
|
214 |
"efficiency": null
|
|
|
217 |
"memory": null,
|
218 |
"latency": {
|
219 |
"unit": "s",
|
220 |
+
"mean": 0.05797825030158548,
|
221 |
+
"stdev": 0.00013128443797395044,
|
222 |
"values": [
|
223 |
+
0.057981952667236325,
|
224 |
+
0.05801062393188477,
|
225 |
+
0.05778227233886719,
|
226 |
+
0.05785295867919922,
|
227 |
+
0.05795939254760742,
|
228 |
+
0.057958560943603514,
|
229 |
+
0.057956192016601564,
|
230 |
+
0.05793894577026367,
|
231 |
+
0.05814076614379883,
|
232 |
+
0.05787535858154297,
|
233 |
+
0.057778175354003904,
|
234 |
+
0.05801369476318359,
|
235 |
+
0.05787347030639649,
|
236 |
+
0.057945022583007814,
|
237 |
+
0.058106880187988284,
|
238 |
+
0.05803113555908203,
|
239 |
+
0.057815006256103516,
|
240 |
+
0.05835673522949219,
|
241 |
+
0.057842689514160155,
|
242 |
+
0.05794815826416016,
|
243 |
+
0.05773635101318359,
|
244 |
+
0.057915489196777345,
|
245 |
+
0.057910110473632814,
|
246 |
+
0.05792655944824219,
|
247 |
+
0.058001407623291014,
|
248 |
+
0.058033153533935546,
|
249 |
+
0.057907424926757815,
|
250 |
+
0.05798691177368164,
|
251 |
+
0.05789996719360352,
|
252 |
+
0.05795840072631836,
|
253 |
+
0.057821182250976565,
|
254 |
+
0.05800755310058594,
|
255 |
+
0.05804544067382812,
|
256 |
+
0.0579788818359375,
|
257 |
+
0.05778636932373047,
|
258 |
+
0.05796659088134765,
|
259 |
+
0.057887935638427736,
|
260 |
+
0.058040126800537106,
|
261 |
+
0.05792563247680664,
|
262 |
+
0.05799939346313476,
|
263 |
+
0.05793788909912109,
|
264 |
+
0.05806284713745117,
|
265 |
+
0.05796659088134765,
|
266 |
+
0.058482688903808595,
|
267 |
+
0.05788684844970703,
|
268 |
+
0.05790201568603515,
|
269 |
+
0.057988094329833983,
|
270 |
+
0.05796550369262695,
|
271 |
+
0.057862144470214844,
|
272 |
+
0.05790924835205078,
|
273 |
+
0.0578600959777832,
|
274 |
+
0.058102783203125,
|
275 |
+
0.057935871124267575,
|
276 |
+
0.057900032043457034,
|
277 |
+
0.05788787078857422,
|
278 |
+
0.057965438842773435,
|
279 |
+
0.05789388656616211,
|
280 |
+
0.05803212738037109,
|
281 |
+
0.057809921264648435,
|
282 |
+
0.057970687866210936,
|
283 |
+
0.05785200119018555,
|
284 |
+
0.05802998352050781,
|
285 |
+
0.05799731063842774,
|
286 |
+
0.058039295196533204,
|
287 |
+
0.05797785568237305,
|
288 |
+
0.058006526947021485,
|
289 |
+
0.05780070495605469,
|
290 |
+
0.057970687866210936,
|
291 |
+
0.05792051315307617,
|
292 |
+
0.057902080535888675,
|
293 |
+
0.057963680267333985,
|
294 |
+
0.057864192962646485,
|
295 |
+
0.0578138542175293,
|
296 |
+
0.05790822219848633,
|
297 |
+
0.05795532989501953,
|
298 |
+
0.057902080535888675,
|
299 |
+
0.057880577087402345,
|
300 |
+
0.05793715286254883,
|
301 |
+
0.05832495880126953,
|
302 |
+
0.05790595245361328,
|
303 |
+
0.058001407623291014,
|
304 |
+
0.05785804748535156,
|
305 |
+
0.05791644668579102,
|
306 |
+
0.058038238525390626,
|
307 |
+
0.057899009704589846,
|
308 |
+
0.05790924835205078,
|
309 |
+
0.058234878540039066,
|
310 |
+
0.05787136077880859,
|
311 |
+
0.05797580718994141,
|
312 |
+
0.057957504272460936,
|
313 |
+
0.058049407958984375,
|
314 |
+
0.05816012954711914,
|
315 |
+
0.05804870223999024,
|
316 |
+
0.058053440093994144,
|
317 |
+
0.0579400634765625,
|
318 |
+
0.058133438110351564,
|
319 |
+
0.058049503326416015,
|
320 |
+
0.05799219131469727,
|
321 |
+
0.057975902557373046,
|
322 |
+
0.05806070327758789,
|
323 |
+
0.05809971237182617,
|
324 |
+
0.057882625579833986,
|
325 |
+
0.05795849609375,
|
326 |
+
0.05792451095581055,
|
327 |
+
0.057896961212158204,
|
328 |
+
0.05785497665405273,
|
329 |
+
0.057821182250976565,
|
330 |
+
0.05796579360961914,
|
331 |
+
0.057914142608642576,
|
332 |
+
0.05799935913085937,
|
333 |
+
0.057952255249023435,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
334 |
0.05785804748535156,
|
335 |
+
0.05787340927124023,
|
336 |
+
0.058022911071777344,
|
337 |
+
0.05783244705200195,
|
338 |
+
0.05785497665405273,
|
339 |
+
0.05785804748535156,
|
340 |
+
0.05777305603027344,
|
341 |
+
0.0578416633605957,
|
342 |
+
0.0579535026550293,
|
343 |
+
0.0578383674621582,
|
344 |
+
0.05821747207641602,
|
345 |
+
0.05771878433227539,
|
346 |
+
0.05779455947875976,
|
347 |
+
0.05780073547363281,
|
348 |
+
0.05784880065917969,
|
349 |
+
0.05769113540649414,
|
350 |
+
0.0577935676574707,
|
351 |
+
0.057997280120849606,
|
352 |
+
0.05788159942626953,
|
353 |
+
0.05786111831665039,
|
354 |
+
0.05796044921875,
|
355 |
+
0.05796659088134765,
|
356 |
+
0.05797683334350586,
|
357 |
+
0.05802700805664063,
|
358 |
+
0.05804873657226563,
|
359 |
+
0.05790915298461914,
|
360 |
+
0.058027904510498045,
|
361 |
+
0.05800960159301758,
|
362 |
+
0.0578600959777832,
|
363 |
+
0.057853950500488284,
|
364 |
+
0.05801881790161133,
|
365 |
+
0.05797273635864258,
|
366 |
+
0.05789286422729492,
|
367 |
+
0.057896961212158204,
|
368 |
+
0.058031105041503904,
|
369 |
+
0.05790617752075195,
|
370 |
+
0.05802700805664063,
|
371 |
+
0.058475681304931644,
|
372 |
+
0.05806166458129883,
|
373 |
+
0.05790924835205078,
|
374 |
+
0.057893951416015624,
|
375 |
+
0.0579543342590332,
|
376 |
+
0.05795830535888672,
|
377 |
+
0.05807820892333984,
|
378 |
+
0.0576993293762207,
|
379 |
+
0.058327041625976565,
|
380 |
+
0.057957374572753906,
|
381 |
+
0.058060798645019535,
|
382 |
+
0.05800348663330078,
|
383 |
+
0.05794198226928711,
|
384 |
+
0.05783859252929688,
|
385 |
+
0.05785497665405273,
|
386 |
+
0.05787750244140625,
|
387 |
+
0.05795430374145508,
|
388 |
+
0.057979969024658205,
|
389 |
+
0.05779142379760742,
|
390 |
+
0.0580055046081543,
|
391 |
+
0.0578682861328125,
|
392 |
+
0.05795942306518555,
|
393 |
+
0.05786624145507813,
|
394 |
+
0.057965568542480465,
|
395 |
+
0.05790822219848633,
|
396 |
+
0.05798835372924805,
|
397 |
+
0.05797881698608399,
|
398 |
+
0.05789168167114258,
|
399 |
+
0.05796860885620117,
|
400 |
+
0.058003456115722656,
|
401 |
+
0.05795635223388672,
|
402 |
+
0.057965568542480465,
|
403 |
+
0.05784678268432617,
|
404 |
+
0.0580055046081543,
|
405 |
+
0.058215614318847655,
|
406 |
+
0.057968448638916016,
|
407 |
+
0.05778227233886719,
|
408 |
+
0.057998336791992185,
|
409 |
+
0.057783294677734375,
|
410 |
+
0.058041343688964846,
|
411 |
+
0.05801062393188477,
|
412 |
+
0.05808230209350586,
|
413 |
+
0.05796873474121094,
|
414 |
+
0.05840681457519531,
|
415 |
+
0.05803417587280273,
|
416 |
+
0.05817753601074219,
|
417 |
+
0.05808025741577148,
|
418 |
+
0.058019840240478515,
|
419 |
+
0.05805372619628906,
|
420 |
+
0.05796239852905274,
|
421 |
+
0.0580208625793457,
|
422 |
+
0.057912353515625,
|
423 |
+
0.05808022308349609,
|
424 |
+
0.05798912048339844,
|
425 |
+
0.05793791961669922,
|
426 |
+
0.05787859344482422,
|
427 |
+
0.05798393630981445,
|
428 |
+
0.0580208625793457,
|
429 |
+
0.05779763031005859,
|
430 |
+
0.05786111831665039,
|
431 |
+
0.05799321746826172,
|
432 |
+
0.05794713592529297,
|
433 |
+
0.05788774490356445,
|
434 |
+
0.057747455596923826,
|
435 |
+
0.057990238189697264,
|
436 |
+
0.05803203201293945,
|
437 |
+
0.058036224365234375,
|
438 |
+
0.05795942306518555,
|
439 |
+
0.05806284713745117,
|
440 |
+
0.05828403091430664,
|
441 |
+
0.058155200958251954,
|
442 |
+
0.058161983489990236,
|
443 |
+
0.05816524887084961,
|
444 |
+
0.058065921783447265,
|
445 |
+
0.05815500640869141,
|
446 |
+
0.05827276611328125,
|
447 |
+
0.05809664154052734,
|
448 |
+
0.05852691268920898,
|
449 |
+
0.05812211227416992,
|
450 |
+
0.057974720001220705,
|
451 |
+
0.058176513671875,
|
452 |
+
0.05809686279296875,
|
453 |
+
0.05809756851196289,
|
454 |
+
0.058137470245361325,
|
455 |
+
0.058068992614746094,
|
456 |
+
0.058017951965332035,
|
457 |
+
0.05806883239746094,
|
458 |
+
0.058014720916748044,
|
459 |
+
0.058103809356689455,
|
460 |
+
0.0579420166015625,
|
461 |
+
0.05811404800415039,
|
462 |
+
0.058038272857666016,
|
463 |
+
0.05810892868041992,
|
464 |
+
0.05799945449829102,
|
465 |
+
0.05804636764526367,
|
466 |
+
0.057892097473144534,
|
467 |
+
0.05815679931640625,
|
468 |
+
0.05814374542236328,
|
469 |
+
0.05808332824707031,
|
470 |
+
0.05796454238891602,
|
471 |
+
0.058089630126953125,
|
472 |
+
0.05783433532714844,
|
473 |
+
0.05796265411376953,
|
474 |
+
0.05796028900146484,
|
475 |
+
0.05845711898803711,
|
476 |
+
0.05792252731323242,
|
477 |
+
0.05818185424804687
|
478 |
]
|
479 |
},
|
480 |
"throughput": {
|
481 |
"unit": "tokens/s",
|
482 |
+
"value": 17.247847163346595
|
483 |
},
|
484 |
"energy": null,
|
485 |
"efficiency": null
|