Upload /Llama-2-13b-hf/nf4_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json with huggingface_hub
Browse files
Llama-2-13b-hf/nf4_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json
CHANGED
@@ -2,141 +2,141 @@
|
|
2 |
"prefill": {
|
3 |
"memory": {
|
4 |
"unit": "MB",
|
5 |
-
"max_ram": 1019.
|
6 |
"max_vram": 8359.247872,
|
7 |
"max_reserved": 7874.80576,
|
8 |
"max_allocated": 7776.413184
|
9 |
},
|
10 |
"latency": {
|
11 |
"unit": "s",
|
12 |
-
"mean": 0.
|
13 |
-
"stdev": 0.
|
14 |
"values": [
|
15 |
-
0.
|
16 |
-
0.
|
17 |
-
0.
|
18 |
-
0.
|
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 |
-
0.08348876953125,
|
32 |
-
0.08336589050292968,
|
33 |
-
0.08354508972167969,
|
34 |
-
0.08330137634277343,
|
35 |
-
0.08355840301513671,
|
36 |
-
0.08343961334228515,
|
37 |
-
0.08356352233886719,
|
38 |
-
0.08346419525146484,
|
39 |
-
0.08360652923583985,
|
40 |
0.08351846313476563,
|
41 |
-
0.
|
42 |
-
0.
|
43 |
-
0.
|
44 |
-
0.
|
45 |
-
0.
|
46 |
-
0.
|
47 |
-
0.
|
48 |
-
0.
|
49 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
0.0835420150756836,
|
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 |
0.08356658935546875,
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
0.08365465545654296,
|
67 |
-
0.
|
68 |
-
0.
|
69 |
-
0.
|
70 |
-
0.0836485137939453,
|
71 |
-
0.08347545623779297,
|
72 |
-
0.08364543914794922,
|
73 |
-
0.08351232147216797,
|
74 |
-
0.08361478424072266,
|
75 |
-
0.0835594253540039,
|
76 |
-
0.08360447692871094,
|
77 |
-
0.08349491119384765,
|
78 |
-
0.0835389404296875,
|
79 |
-
0.08356147003173828,
|
80 |
-
0.08361984252929687,
|
81 |
-
0.08354713439941407,
|
82 |
-
0.08363008117675781,
|
83 |
-
0.08351846313476563,
|
84 |
-
0.08367411041259766,
|
85 |
-
0.08348473358154297,
|
86 |
0.0836659164428711,
|
87 |
-
0.
|
88 |
-
0.
|
89 |
-
0.
|
90 |
-
0.
|
91 |
-
0.
|
92 |
-
0.
|
93 |
-
0.
|
94 |
-
0.
|
95 |
-
0.08363314819335937,
|
96 |
-
0.08359423828125,
|
97 |
-
0.08361164855957032,
|
98 |
-
0.08357068634033203,
|
99 |
-
0.08360755157470703,
|
100 |
-
0.08362086486816406,
|
101 |
0.08364031982421875,
|
102 |
-
0.
|
103 |
-
0.0836648941040039,
|
104 |
-
0.08355532836914062,
|
105 |
-
0.08365567779541015,
|
106 |
-
0.08343654632568359,
|
107 |
-
0.08357785797119141,
|
108 |
0.08364339447021485,
|
109 |
-
0.
|
110 |
-
0.
|
111 |
-
0.
|
112 |
-
0.
|
113 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
0.08363212585449219,
|
115 |
-
0.
|
116 |
-
0.
|
117 |
-
0.
|
118 |
-
0.
|
119 |
-
0.
|
120 |
-
0.
|
121 |
-
0.
|
122 |
-
0.08357273864746094,
|
123 |
-
0.08354918670654297,
|
124 |
-
0.08361472320556641,
|
125 |
-
0.0835758056640625,
|
126 |
-
0.0836157455444336,
|
127 |
-
0.083736572265625,
|
128 |
-
0.08359935760498047,
|
129 |
-
0.08367001342773438,
|
130 |
-
0.08368434906005859,
|
131 |
-
0.08361676788330077,
|
132 |
0.08370073699951172,
|
133 |
-
0.
|
134 |
-
0.
|
|
|
|
|
|
|
135 |
]
|
136 |
},
|
137 |
"throughput": {
|
138 |
"unit": "tokens/s",
|
139 |
-
"value": 3061.
|
140 |
},
|
141 |
"energy": null,
|
142 |
"efficiency": null
|
@@ -144,22 +144,22 @@
|
|
144 |
"decode": {
|
145 |
"memory": {
|
146 |
"unit": "MB",
|
147 |
-
"max_ram": 1019.
|
148 |
"max_vram": 9105.833984,
|
149 |
"max_reserved": 8621.391872,
|
150 |
-
"max_allocated": 8484.
|
151 |
},
|
152 |
"latency": {
|
153 |
"unit": "s",
|
154 |
-
"mean": 10.
|
155 |
"stdev": 0,
|
156 |
"values": [
|
157 |
-
10.
|
158 |
]
|
159 |
},
|
160 |
"throughput": {
|
161 |
"unit": "tokens/s",
|
162 |
-
"value":
|
163 |
},
|
164 |
"energy": null,
|
165 |
"efficiency": null
|
@@ -168,269 +168,269 @@
|
|
168 |
"memory": null,
|
169 |
"latency": {
|
170 |
"unit": "s",
|
171 |
-
"mean": 0.
|
172 |
-
"stdev": 0.
|
173 |
"values": [
|
174 |
-
0.
|
175 |
-
0.
|
176 |
-
0.
|
177 |
-
0.
|
178 |
-
0.
|
179 |
-
0.
|
180 |
-
0.
|
181 |
-
0.04190729522705078,
|
182 |
-
0.041731998443603514,
|
183 |
-
0.0417097282409668,
|
184 |
-
0.04163772964477539,
|
185 |
-
0.041665534973144534,
|
186 |
-
0.04169113540649414,
|
187 |
-
0.04170444869995117,
|
188 |
-
0.041525344848632816,
|
189 |
-
0.041611392974853514,
|
190 |
-
0.041853729248046874,
|
191 |
-
0.041670654296875,
|
192 |
-
0.04159078216552734,
|
193 |
-
0.0422031364440918,
|
194 |
-
0.04166348648071289,
|
195 |
-
0.04166144180297852,
|
196 |
-
0.04178636932373047,
|
197 |
-
0.04178227233886719,
|
198 |
-
0.04161740875244141,
|
199 |
-
0.041637889862060545,
|
200 |
-
0.041540607452392575,
|
201 |
-
0.041680896759033206,
|
202 |
-
0.04149350357055664,
|
203 |
-
0.041853950500488284,
|
204 |
-
0.04163891220092773,
|
205 |
-
0.042157054901123044,
|
206 |
-
0.041724929809570314,
|
207 |
-
0.04184678268432617,
|
208 |
-
0.04176998519897461,
|
209 |
-
0.04156313705444336,
|
210 |
-
0.041793537139892575,
|
211 |
-
0.04184064102172851,
|
212 |
-
0.041731071472167966,
|
213 |
-
0.04159795379638672,
|
214 |
-
0.041635841369628904,
|
215 |
-
0.041799678802490234,
|
216 |
-
0.04178841781616211,
|
217 |
-
0.04166860961914062,
|
218 |
-
0.04155392074584961,
|
219 |
-
0.04159795379638672,
|
220 |
-
0.04189081573486328,
|
221 |
-
0.04163593673706055,
|
222 |
-
0.04162140655517578,
|
223 |
-
0.041591808319091796,
|
224 |
-
0.04174848175048828,
|
225 |
-
0.04168505477905273,
|
226 |
-
0.04173100662231445,
|
227 |
-
0.04184883117675781,
|
228 |
-
0.04174335861206055,
|
229 |
-
0.04178636932373047,
|
230 |
-
0.04176998519897461,
|
231 |
-
0.04193280029296875,
|
232 |
-
0.04166451263427735,
|
233 |
-
0.04170649719238281,
|
234 |
-
0.041626625061035157,
|
235 |
-
0.04183552169799805,
|
236 |
-
0.0415549430847168,
|
237 |
-
0.04173619079589844,
|
238 |
-
0.04194303894042969,
|
239 |
-
0.04162876892089844,
|
240 |
-
0.041638816833496094,
|
241 |
-
0.04215091323852539,
|
242 |
-
0.041744384765625,
|
243 |
-
0.0415428466796875,
|
244 |
-
0.04168377685546875,
|
245 |
-
0.04152937698364258,
|
246 |
-
0.04166140747070313,
|
247 |
-
0.0417259521484375,
|
248 |
-
0.04163993453979492,
|
249 |
-
0.04149248123168945,
|
250 |
-
0.041828353881835936,
|
251 |
-
0.04155801773071289,
|
252 |
-
0.04156825637817383,
|
253 |
-
0.04218163299560547,
|
254 |
-
0.04151910400390625,
|
255 |
-
0.04177519989013672,
|
256 |
-
0.041640865325927735,
|
257 |
-
0.04164198303222656,
|
258 |
-
0.04178841781616211,
|
259 |
-
0.04186127853393555,
|
260 |
-
0.041912158966064456,
|
261 |
-
0.04161228942871094,
|
262 |
-
0.04188774490356445,
|
263 |
-
0.041880577087402344,
|
264 |
-
0.04161228942871094,
|
265 |
-
0.04169126510620117,
|
266 |
-
0.041487232208251956,
|
267 |
-
0.04148857498168945,
|
268 |
-
0.04159161758422852,
|
269 |
-
0.04171980667114258,
|
270 |
-
0.04153855895996094,
|
271 |
-
0.04185190582275391,
|
272 |
-
0.04175769424438477,
|
273 |
-
0.04186223983764648,
|
274 |
-
0.04184156799316406,
|
275 |
-
0.04189801788330078,
|
276 |
-
0.04187030410766602,
|
277 |
-
0.041836544036865236,
|
278 |
-
0.041780223846435545,
|
279 |
-
0.041708545684814455,
|
280 |
-
0.04182425689697265,
|
281 |
-
0.04182947158813476,
|
282 |
-
0.04204636764526367,
|
283 |
-
0.041854209899902343,
|
284 |
-
0.041729793548583985,
|
285 |
0.04175974273681641,
|
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 |
-
0.04178636932373047,
|
320 |
-
0.04187238311767578,
|
321 |
-
0.041665534973144534,
|
322 |
-
0.04189286422729492,
|
323 |
-
0.04149760055541992,
|
324 |
-
0.04184473419189453,
|
325 |
-
0.04191436767578125,
|
326 |
-
0.04183244705200195,
|
327 |
-
0.042280223846435545,
|
328 |
-
0.042299102783203125,
|
329 |
-
0.04186214447021484,
|
330 |
-
0.04178841781616211,
|
331 |
-
0.04185497665405274,
|
332 |
-
0.04175769424438477,
|
333 |
-
0.04167782211303711,
|
334 |
-
0.04173516845703125,
|
335 |
-
0.041816062927246093,
|
336 |
-
0.04177203369140625,
|
337 |
-
0.0417894401550293,
|
338 |
-
0.042105857849121096,
|
339 |
-
0.04157654571533203,
|
340 |
-
0.04186614227294922,
|
341 |
-
0.041842689514160154,
|
342 |
-
0.041605121612548826,
|
343 |
-
0.04171878433227539,
|
344 |
-
0.041629695892333986,
|
345 |
-
0.041875457763671874,
|
346 |
-
0.04161536026000977,
|
347 |
-
0.04171366500854492,
|
348 |
-
0.04176588821411133,
|
349 |
-
0.04219596862792969,
|
350 |
-
0.04166144180297852,
|
351 |
-
0.04165836715698242,
|
352 |
-
0.041659393310546876,
|
353 |
-
0.04185625457763672,
|
354 |
-
0.04177382278442383,
|
355 |
-
0.04182732772827148,
|
356 |
-
0.041847808837890625,
|
357 |
-
0.041826305389404295,
|
358 |
-
0.04172083282470703,
|
359 |
-
0.04182527923583984,
|
360 |
-
0.0418600959777832,
|
361 |
-
0.04174950408935547,
|
362 |
-
0.04171571350097656,
|
363 |
-
0.041708545684814455,
|
364 |
-
0.04163686370849609,
|
365 |
-
0.04158464050292969,
|
366 |
-
0.041665534973144534,
|
367 |
-
0.04190719985961914,
|
368 |
-
0.041680896759033206,
|
369 |
-
0.041777153015136716,
|
370 |
-
0.041534465789794923,
|
371 |
-
0.04157136154174805,
|
372 |
-
0.04159382247924805,
|
373 |
-
0.04162355041503906,
|
374 |
-
0.04171571350097656,
|
375 |
-
0.041673728942871094,
|
376 |
-
0.041724929809570314,
|
377 |
-
0.041665534973144534,
|
378 |
-
0.041594879150390625,
|
379 |
-
0.04173209762573242,
|
380 |
-
0.04168294525146484,
|
381 |
-
0.04171980667114258,
|
382 |
-
0.0416890869140625,
|
383 |
-
0.04168601608276367,
|
384 |
-
0.041556991577148435,
|
385 |
-
0.041712928771972656,
|
386 |
-
0.042162910461425784,
|
387 |
-
0.04135424041748047,
|
388 |
-
0.04165119934082031,
|
389 |
-
0.04175872039794922,
|
390 |
-
0.04175564956665039,
|
391 |
-
0.041715999603271485,
|
392 |
-
0.041715423583984376,
|
393 |
-
0.041567230224609376,
|
394 |
-
0.04177305603027344,
|
395 |
-
0.04170348739624023,
|
396 |
-
0.041805759429931644,
|
397 |
-
0.041662464141845705,
|
398 |
-
0.04213555145263672,
|
399 |
-
0.04206489562988281,
|
400 |
-
0.04169113540649414,
|
401 |
-
0.04160531234741211,
|
402 |
-
0.041748287200927735,
|
403 |
-
0.04173516845703125,
|
404 |
-
0.041632766723632815,
|
405 |
-
0.04172902297973633,
|
406 |
-
0.04197683334350586,
|
407 |
-
0.041750526428222655,
|
408 |
-
0.041635841369628904,
|
409 |
-
0.04169318389892578,
|
410 |
-
0.04157747268676758,
|
411 |
-
0.041750526428222655,
|
412 |
-
0.04165017700195312,
|
413 |
-
0.04164198303222656,
|
414 |
0.04153855895996094,
|
415 |
-
0.
|
416 |
-
0.
|
417 |
-
0.
|
418 |
-
0.
|
419 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
420 |
0.041971710205078124,
|
421 |
-
0.
|
422 |
-
0.
|
423 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
424 |
0.041545726776123046,
|
425 |
-
0.
|
426 |
-
0.
|
427 |
-
0.
|
428 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
429 |
]
|
430 |
},
|
431 |
"throughput": {
|
432 |
"unit": "tokens/s",
|
433 |
-
"value":
|
434 |
},
|
435 |
"energy": null,
|
436 |
"efficiency": null
|
|
|
2 |
"prefill": {
|
3 |
"memory": {
|
4 |
"unit": "MB",
|
5 |
+
"max_ram": 1019.375616,
|
6 |
"max_vram": 8359.247872,
|
7 |
"max_reserved": 7874.80576,
|
8 |
"max_allocated": 7776.413184
|
9 |
},
|
10 |
"latency": {
|
11 |
"unit": "s",
|
12 |
+
"mean": 0.08363019695281983,
|
13 |
+
"stdev": 0.0003531849560279038,
|
14 |
"values": [
|
15 |
+
0.08732947540283204,
|
16 |
+
0.08376319885253906,
|
17 |
+
0.083957763671875,
|
18 |
+
0.0838809585571289,
|
19 |
+
0.08340582275390625,
|
20 |
+
0.08363212585449219,
|
21 |
+
0.08374066925048829,
|
22 |
+
0.08372736358642578,
|
23 |
+
0.08356150054931641,
|
24 |
+
0.08356674957275391,
|
25 |
+
0.08352870178222656,
|
26 |
+
0.08333721923828125,
|
27 |
+
0.08359833526611328,
|
28 |
+
0.08344985961914063,
|
29 |
+
0.08359526062011718,
|
30 |
+
0.08359526062011718,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
0.08351846313476563,
|
32 |
+
0.08339148712158204,
|
33 |
+
0.08352665710449218,
|
34 |
+
0.08335769653320313,
|
35 |
+
0.0835819549560547,
|
36 |
+
0.08344166564941406,
|
37 |
+
0.08362905883789062,
|
38 |
+
0.08351641845703126,
|
39 |
+
0.08358502197265626,
|
40 |
+
0.08353997039794922,
|
41 |
+
0.08359833526611328,
|
42 |
+
0.08341913604736328,
|
43 |
+
0.08358399963378907,
|
44 |
+
0.08345394897460938,
|
45 |
+
0.0835594253540039,
|
46 |
+
0.08357068634033203,
|
47 |
+
0.08361062622070313,
|
48 |
+
0.08357382202148438,
|
49 |
+
0.08353596496582032,
|
50 |
+
0.08361472320556641,
|
51 |
+
0.08351744079589844,
|
52 |
+
0.08368434906005859,
|
53 |
+
0.08358911895751953,
|
54 |
+
0.08367001342773438,
|
55 |
0.0835420150756836,
|
56 |
+
0.0836126708984375,
|
57 |
+
0.08337920379638672,
|
58 |
+
0.0836341781616211,
|
59 |
+
0.08347443389892578,
|
60 |
+
0.08360969543457031,
|
61 |
+
0.08359423828125,
|
62 |
+
0.08370073699951172,
|
63 |
+
0.08353177642822265,
|
64 |
+
0.08351744079589844,
|
65 |
+
0.08354611206054688,
|
66 |
+
0.08370687866210938,
|
67 |
+
0.08353791809082031,
|
68 |
+
0.08374681854248046,
|
69 |
+
0.08353075408935547,
|
70 |
+
0.08368537902832031,
|
71 |
+
0.0835072021484375,
|
72 |
+
0.08369971466064453,
|
73 |
+
0.08352153778076171,
|
74 |
+
0.08364441680908204,
|
75 |
0.08356658935546875,
|
76 |
+
0.08365171051025391,
|
77 |
+
0.0835072021484375,
|
78 |
+
0.0835788803100586,
|
79 |
+
0.0835819549560547,
|
80 |
+
0.08368844604492187,
|
81 |
+
0.08360057830810547,
|
82 |
0.08365465545654296,
|
83 |
+
0.08356352233886719,
|
84 |
+
0.08372633361816406,
|
85 |
+
0.08350617980957031,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
0.0836659164428711,
|
87 |
+
0.08357376098632813,
|
88 |
+
0.08371711730957031,
|
89 |
+
0.08338739013671875,
|
90 |
+
0.08364236450195313,
|
91 |
+
0.0837232666015625,
|
92 |
+
0.08367820739746094,
|
93 |
+
0.08354815673828125,
|
94 |
+
0.08364659118652344,
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
0.08364031982421875,
|
96 |
+
0.08358809661865234,
|
|
|
|
|
|
|
|
|
|
|
97 |
0.08364339447021485,
|
98 |
+
0.0835788803100586,
|
99 |
+
0.08363314819335937,
|
100 |
+
0.08358604431152344,
|
101 |
+
0.08369356536865234,
|
102 |
+
0.08365158081054687,
|
103 |
+
0.08367513275146485,
|
104 |
+
0.08359219360351562,
|
105 |
+
0.08369049835205078,
|
106 |
+
0.08345292663574219,
|
107 |
+
0.08387276458740234,
|
108 |
+
0.08367922973632813,
|
109 |
+
0.08362905883789062,
|
110 |
+
0.08358399963378907,
|
111 |
+
0.08357478332519531,
|
112 |
+
0.08351232147216797,
|
113 |
+
0.08364150238037109,
|
114 |
+
0.08361779022216796,
|
115 |
+
0.08365055847167968,
|
116 |
+
0.08356556701660156,
|
117 |
+
0.08363622283935547,
|
118 |
+
0.08354713439941407,
|
119 |
+
0.083631103515625,
|
120 |
+
0.0835788803100586,
|
121 |
0.08363212585449219,
|
122 |
+
0.08355430603027343,
|
123 |
+
0.0835420150756836,
|
124 |
+
0.08362188720703125,
|
125 |
+
0.08357990264892579,
|
126 |
+
0.08364543914794922,
|
127 |
+
0.08374066925048829,
|
128 |
+
0.08362496185302734,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
0.08370073699951172,
|
130 |
+
0.08369664001464844,
|
131 |
+
0.08363520050048828,
|
132 |
+
0.08368025970458984,
|
133 |
+
0.08363008117675781,
|
134 |
+
0.08352051544189452
|
135 |
]
|
136 |
},
|
137 |
"throughput": {
|
138 |
"unit": "tokens/s",
|
139 |
+
"value": 3061.09526615635
|
140 |
},
|
141 |
"energy": null,
|
142 |
"efficiency": null
|
|
|
144 |
"decode": {
|
145 |
"memory": {
|
146 |
"unit": "MB",
|
147 |
+
"max_ram": 1019.375616,
|
148 |
"max_vram": 9105.833984,
|
149 |
"max_reserved": 8621.391872,
|
150 |
+
"max_allocated": 8484.938752
|
151 |
},
|
152 |
"latency": {
|
153 |
"unit": "s",
|
154 |
+
"mean": 10.570713066101069,
|
155 |
"stdev": 0,
|
156 |
"values": [
|
157 |
+
10.570713066101069
|
158 |
]
|
159 |
},
|
160 |
"throughput": {
|
161 |
"unit": "tokens/s",
|
162 |
+
"value": 24.12325435431149
|
163 |
},
|
164 |
"energy": null,
|
165 |
"efficiency": null
|
|
|
168 |
"memory": null,
|
169 |
"latency": {
|
170 |
"unit": "s",
|
171 |
+
"mean": 0.041453776729808114,
|
172 |
+
"stdev": 0.0001673921734561523,
|
173 |
"values": [
|
174 |
+
0.04201593780517578,
|
175 |
+
0.042260288238525394,
|
176 |
+
0.04128076934814453,
|
177 |
+
0.04130892944335938,
|
178 |
+
0.04147942352294922,
|
179 |
+
0.041406208038330075,
|
180 |
+
0.04157440185546875,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
0.04175974273681641,
|
182 |
+
0.04134604644775391,
|
183 |
+
0.04144963073730469,
|
184 |
+
0.041427806854248045,
|
185 |
+
0.04130009460449219,
|
186 |
+
0.04140838241577149,
|
187 |
+
0.04185702514648437,
|
188 |
+
0.04133302307128906,
|
189 |
+
0.04144508743286133,
|
190 |
+
0.04121395111083984,
|
191 |
+
0.04165631866455078,
|
192 |
+
0.04146585464477539,
|
193 |
+
0.041468929290771485,
|
194 |
+
0.04134809494018555,
|
195 |
+
0.04151398468017578,
|
196 |
+
0.041250816345214845,
|
197 |
+
0.04140771102905273,
|
198 |
+
0.0418383674621582,
|
199 |
+
0.041368576049804685,
|
200 |
+
0.0413675537109375,
|
201 |
+
0.04146380615234375,
|
202 |
+
0.04143308639526367,
|
203 |
+
0.04145379257202148,
|
204 |
+
0.04152511978149414,
|
205 |
+
0.04150588989257813,
|
206 |
+
0.041404224395751955,
|
207 |
+
0.04174140930175781,
|
208 |
+
0.04129481506347656,
|
209 |
+
0.04145043182373047,
|
210 |
+
0.04154265594482422,
|
211 |
+
0.041468929290771485,
|
212 |
+
0.04139139175415039,
|
213 |
+
0.04156796646118164,
|
214 |
+
0.04136038589477539,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
0.04153855895996094,
|
216 |
+
0.04157132720947266,
|
217 |
+
0.041356353759765624,
|
218 |
+
0.04123129653930664,
|
219 |
+
0.04129894256591797,
|
220 |
+
0.041336830139160154,
|
221 |
+
0.041186302185058594,
|
222 |
+
0.04126310348510742,
|
223 |
+
0.041221118927001955,
|
224 |
+
0.041175201416015626,
|
225 |
+
0.04118716812133789,
|
226 |
+
0.04113612747192383,
|
227 |
+
0.041400417327880856,
|
228 |
+
0.04129679870605469,
|
229 |
+
0.04144947052001953,
|
230 |
+
0.041543678283691404,
|
231 |
+
0.04138086318969727,
|
232 |
+
0.041473312377929686,
|
233 |
+
0.04135721588134766,
|
234 |
+
0.041269214630126956,
|
235 |
+
0.04157014465332031,
|
236 |
+
0.04137984085083008,
|
237 |
+
0.04141363143920898,
|
238 |
+
0.041441566467285154,
|
239 |
+
0.04162838363647461,
|
240 |
+
0.04131532669067383,
|
241 |
+
0.041278465270996094,
|
242 |
+
0.04131327819824219,
|
243 |
+
0.04143206405639648,
|
244 |
+
0.04128566360473633,
|
245 |
+
0.04144534301757812,
|
246 |
+
0.04116070556640625,
|
247 |
+
0.04171673583984375,
|
248 |
+
0.04120985412597656,
|
249 |
+
0.04153139114379883,
|
250 |
+
0.04135628890991211,
|
251 |
+
0.0415285758972168,
|
252 |
+
0.041528289794921874,
|
253 |
+
0.041506591796875,
|
254 |
+
0.04146278381347656,
|
255 |
+
0.04167475128173828,
|
256 |
+
0.04147814559936523,
|
257 |
+
0.04133174514770508,
|
258 |
+
0.041212894439697265,
|
259 |
+
0.04150783920288086,
|
260 |
+
0.041481281280517576,
|
261 |
+
0.041410495758056644,
|
262 |
+
0.041488384246826174,
|
263 |
+
0.04154163360595703,
|
264 |
+
0.04141670227050781,
|
265 |
+
0.041414657592773435,
|
266 |
+
0.041326656341552734,
|
267 |
+
0.041427902221679684,
|
268 |
+
0.04147222518920898,
|
269 |
+
0.04126697540283203,
|
270 |
+
0.041076736450195314,
|
271 |
+
0.04139929580688476,
|
272 |
+
0.04119667053222656,
|
273 |
+
0.041363327026367185,
|
274 |
+
0.041416801452636716,
|
275 |
+
0.041471038818359375,
|
276 |
+
0.0412762565612793,
|
277 |
+
0.04148019027709961,
|
278 |
+
0.04108902359008789,
|
279 |
+
0.04132659149169922,
|
280 |
+
0.04142489624023438,
|
281 |
+
0.041280513763427736,
|
282 |
+
0.04137881469726563,
|
283 |
+
0.041491455078125,
|
284 |
+
0.0416071662902832,
|
285 |
+
0.04127948760986328,
|
286 |
+
0.041335807800292966,
|
287 |
+
0.041283584594726565,
|
288 |
+
0.04135321426391601,
|
289 |
+
0.04151311874389649,
|
290 |
+
0.04164080047607422,
|
291 |
+
0.041452545166015625,
|
292 |
+
0.04143820953369141,
|
293 |
+
0.04148428726196289,
|
294 |
+
0.04135833740234375,
|
295 |
+
0.04153343963623047,
|
296 |
+
0.041837566375732424,
|
297 |
+
0.04139123153686523,
|
298 |
+
0.04149871826171875,
|
299 |
+
0.04161727905273437,
|
300 |
+
0.041551807403564456,
|
301 |
+
0.041468894958496094,
|
302 |
+
0.04149964904785156,
|
303 |
+
0.04165324783325195,
|
304 |
+
0.041398273468017575,
|
305 |
+
0.04132044982910156,
|
306 |
+
0.04149964904785156,
|
307 |
+
0.04148019027709961,
|
308 |
+
0.041390079498291016,
|
309 |
+
0.04143011093139649,
|
310 |
+
0.04157430267333984,
|
311 |
+
0.04169446563720703,
|
312 |
+
0.04150143814086914,
|
313 |
+
0.041485313415527345,
|
314 |
+
0.041474048614501956,
|
315 |
+
0.041626625061035157,
|
316 |
+
0.0413675537109375,
|
317 |
+
0.04150579071044922,
|
318 |
+
0.041576446533203124,
|
319 |
+
0.04151603317260742,
|
320 |
+
0.04175155258178711,
|
321 |
+
0.041441280364990236,
|
322 |
+
0.041606143951416014,
|
323 |
+
0.04152627182006836,
|
324 |
+
0.04145663833618164,
|
325 |
+
0.04156620788574219,
|
326 |
+
0.041568321228027345,
|
327 |
+
0.04196448135375976,
|
328 |
+
0.04197478485107422,
|
329 |
+
0.04153139114379883,
|
330 |
+
0.041640960693359375,
|
331 |
+
0.041388031005859374,
|
332 |
+
0.041439231872558595,
|
333 |
+
0.042120193481445314,
|
334 |
+
0.04157235336303711,
|
335 |
+
0.041666847229003906,
|
336 |
+
0.04175024032592774,
|
337 |
+
0.04152336120605469,
|
338 |
+
0.041484127044677736,
|
339 |
+
0.04150175857543945,
|
340 |
+
0.04153747177124024,
|
341 |
+
0.04151091384887695,
|
342 |
+
0.04138620758056641,
|
343 |
+
0.04149020767211914,
|
344 |
0.041971710205078124,
|
345 |
+
0.041603073120117184,
|
346 |
+
0.041451583862304686,
|
347 |
+
0.04141766357421875,
|
348 |
+
0.04148847961425781,
|
349 |
+
0.041494560241699216,
|
350 |
+
0.041430912017822265,
|
351 |
+
0.041444446563720705,
|
352 |
+
0.0414483528137207,
|
353 |
+
0.04139212799072266,
|
354 |
+
0.04155084609985352,
|
355 |
0.041545726776123046,
|
356 |
+
0.04165222549438476,
|
357 |
+
0.041518081665039064,
|
358 |
+
0.04158054351806641,
|
359 |
+
0.04149657440185547,
|
360 |
+
0.04148735809326172,
|
361 |
+
0.0415365104675293,
|
362 |
+
0.04160204696655274,
|
363 |
+
0.04157440185546875,
|
364 |
+
0.041578495025634765,
|
365 |
+
0.041578590393066404,
|
366 |
+
0.0415722541809082,
|
367 |
+
0.041619457244873044,
|
368 |
+
0.041482433319091794,
|
369 |
+
0.041346881866455076,
|
370 |
+
0.04150476837158203,
|
371 |
+
0.04127436828613281,
|
372 |
+
0.04145459365844727,
|
373 |
+
0.041444351196289066,
|
374 |
+
0.041524223327636715,
|
375 |
+
0.041312255859375,
|
376 |
+
0.04142387390136719,
|
377 |
+
0.0414730224609375,
|
378 |
+
0.04142899322509765,
|
379 |
+
0.04136675262451172,
|
380 |
+
0.04128028869628906,
|
381 |
+
0.041839935302734374,
|
382 |
+
0.041273025512695315,
|
383 |
+
0.041355262756347655,
|
384 |
+
0.04137881469726563,
|
385 |
+
0.04136243057250977,
|
386 |
+
0.04140240097045898,
|
387 |
+
0.04125900650024414,
|
388 |
+
0.04160713577270508,
|
389 |
+
0.041398273468017575,
|
390 |
+
0.04150783920288086,
|
391 |
+
0.041419776916503906,
|
392 |
+
0.0413809928894043,
|
393 |
+
0.04185279846191406,
|
394 |
+
0.04119756698608398,
|
395 |
+
0.04137267303466797,
|
396 |
+
0.04132044982910156,
|
397 |
+
0.04151939010620117,
|
398 |
+
0.04137648010253906,
|
399 |
+
0.04147328186035156,
|
400 |
+
0.041288448333740235,
|
401 |
+
0.04149555206298828,
|
402 |
+
0.04142182540893555,
|
403 |
+
0.041437217712402344,
|
404 |
+
0.04119244766235351,
|
405 |
+
0.0413603515625,
|
406 |
+
0.041401344299316405,
|
407 |
+
0.041419776916503906,
|
408 |
+
0.041128959655761715,
|
409 |
+
0.04139724731445313,
|
410 |
+
0.04129302215576172,
|
411 |
+
0.04132124710083008,
|
412 |
+
0.04123648071289063,
|
413 |
+
0.041221118927001955,
|
414 |
+
0.04125196838378906,
|
415 |
+
0.04148620986938477,
|
416 |
+
0.041285633087158206,
|
417 |
+
0.04118937683105469,
|
418 |
+
0.04123955154418945,
|
419 |
+
0.04137984085083008,
|
420 |
+
0.041332736968994144,
|
421 |
+
0.04140054321289063,
|
422 |
+
0.041361183166503904,
|
423 |
+
0.041452545166015625,
|
424 |
+
0.041576446533203124,
|
425 |
+
0.04146380615234375,
|
426 |
+
0.04145663833618164,
|
427 |
+
0.041669921875,
|
428 |
+
0.04140412902832031
|
429 |
]
|
430 |
},
|
431 |
"throughput": {
|
432 |
"unit": "tokens/s",
|
433 |
+
"value": 24.12325435431149
|
434 |
},
|
435 |
"energy": null,
|
436 |
"efficiency": null
|