Edge-Inference-Benchmarks / data /all-MiniLM-L6-v2.csv
Magzimilian's picture
Add deploy-benchmark model families (8 models, lat/ips/mem metrics)
45c0521
Raw
History Blame Contribute Delete
241 Bytes
model_family,model,type,batch,device,res,ctx,lat,ips,mem
all-MiniLM-L6-v2,sentence-transformers/all-MiniLM-L6-v2,text,1,agx_orin,N/A,,0.409,2447,43
all-MiniLM-L6-v2,embedl/all-MiniLM-L6-v2-quantized-trt,text,1,agx_orin,N/A,,0.383,2611,36