-
Notifications
You must be signed in to change notification settings - Fork 65
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Neuron SDK v2.19.1 Trainium benchmarking update (#695)
- Loading branch information
Showing
3 changed files
with
22 additions
and
30 deletions.
There are no files selected for viewing
17 changes: 7 additions & 10 deletions
17
benchmark/text-generation-inference/llama3-70b-trn1.32xlarge/tgi-results-batchsize-1.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,8 @@ | ||
| model_id,concurrent requests,throughput (t/s),Time-to-first-token @ P50 (s),average latency (ms) | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,38.29638310438374,0.5521726660008426,24.784959740501066 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,38.98036959617541,2.72243953349971,32.827924415254174 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,39.39299322930307,8.926065296996967,63.795771842799695 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,39.85480734427003,22.479033984491252,110.33245410384168 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,39.797703130119444,48.74777327400079,218.4971534548553 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,39.88112179496438,98.32968477499526,419.0164926030421 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,40.021570341867225,201.50347035600862,787.0418267487788 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,128,40.15190355766733,412.9219288924942,1608.1377339868322 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,256,40.10404829156176,831.7238280020028,3167.7755826448656 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,512,39.94606130182408,1654.066714687011,6348.469898092637 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,47.036052229904286,0.5264043899951503,20.465843433893646 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,47.80577679519902,2.3793273210758343,28.003227711219164 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,48.461899623182426,7.175522217527032,52.262069554218435 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,48.773082055567116,18.760041670990176,84.57645582900525 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,49.25268191199813,38.44228728755843,170.77333503909537 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,49.416289879279326,80.52483583055437,339.16646354168245 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,49.64596189738265,162.74696793837938,653.7145961071376 |
17 changes: 7 additions & 10 deletions
17
benchmark/text-generation-inference/llama3-70b-trn1.32xlarge/tgi-results-batchsize-8.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,8 @@ | ||
| model_id,concurrent requests,throughput (t/s),Time-to-first-token @ P50 (s),average latency (ms) | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,17.8322790536497,0.9939256490033586,54.45429111182844 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,31.140113024869468,1.418605798491626,58.17940704286386 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,52.71447508703364,3.691673280511168,65.510341492747 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,85.23757246875635,7.40343523149204,79.86574747355823 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,83.41704442714865,12.134337133495137,119.80365178993138 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,86.31413401709217,33.19637775150477,221.51387761253872 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,91.54051788296289,78.17263232148252,378.5575452672668 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,128,93.59227409861985,163.85781266850245,709.4836254794548 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,256,94.49695504491365,332.89309809000406,1342.054465909721 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,512,94.76202310893393,671.8385370509932,2633.1926459323054 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,30.427246781641298,0.8465556244991603,31.940039622234323 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,51.814449828727014,1.6578905005007982,35.303453482741524 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,80.2709630081468,3.330909075506497,42.56936121417554 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,123.95265621601503,6.631509564504086,55.705136697349 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,123.41551351427066,9.613880677999987,86.92725453610271 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,129.01888179479806,24.736346793506527,151.7353908036725 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,133.1848930344421,56.04210297649843,269.5292990644778 |
18 changes: 8 additions & 10 deletions
18
benchmark/text-generation-inference/llama3-70b-trn1.32xlarge/tgi-results.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,9 @@ | ||
| model_id,concurrent requests,throughput (t/s),Time-to-first-token @ P50 (s),average latency (ms) | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,27.321283482983713,0.9897541589998582,34.53017190612728 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,47.14780790833105,1.4317841799993403,38.47682874008382 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,75.46880157534952,3.7293467640001836,45.219761063884626 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,76.656177664245,6.710071522500584,67.5562098563004 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,78.10745154737947,18.174910198499674,130.32796764867985 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,80.94695720514072,42.99618862100033,211.52529640942643 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,83.41961944293132,90.68870028399942,387.7336944140728 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,128,84.68410927601217,187.20342993849863,761.1909438667759 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,256,85.08930039980858,376.98190486400017,1484.3806421055476 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,512,84.99711473871804,758.8232675055006,2947.3092666464 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,1,33.13623382956197,0.847853995503101,29.194137679169646 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,2,55.61050569710368,1.2736788609981886,32.90289103801151 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,4,86.58456489701315,3.34435009349545,39.293303536708166 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,8,90.20366126074002,5.904863483490772,55.9280860250687 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,16,93.46094649258835,16.161018327497004,108.1654402765888 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,32,94.60090167352047,37.34856389850029,182.42863576574968 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,64,97.6200946608771,80.71991845800221,357.9967863853603 | ||
| huggingface/NousResearch/Meta-Llama-3-70B-Instruct,128,98.4129882974856,165.12605451900163,684.5967867979082 |