관심있는것들

보호되어 있는 글입니다.

보호되어 있는 글입니다.

in ML Quantization usually mean FP32 -> INT8Usually, when the training of the model is finished, train parameters falls in to simple shallow distribution. scale ? zero-point ? how do i calculate that scale? Z = 207 so we can map 2^b - 1 to 256. S = 0.6/255Linear depends on function , symmetric asymmetric depends on starting point ( 0 == symmetric , otherwise asymmetric)Dequantization cannot repr..

from big picture (Architecture) to actual unit design (Mircro Architecture) , will not cover Circuit  accumulator = adding number (need to hold a number) , adder doesn't need to hold statethis takes O(N) to compute dot product of length n vectors. e.g) 8 cycles if n is 8 usping multiple multiplier will be faster but how to merge the results ,need adder treenow it takes 2 cycle to calculate 8 len..

보호되어 있는 글입니다.

보호되어 있는 글입니다.

보호되어 있는 글입니다.

현재는 JMX MBean기반으로 정보를 export하고 있다. 이 정보들을 actuator로 뿌려줘서 다른 모니터링 팀에서 수월하게 정보를 가져올 수 있게 하자기본적으로 Gague.builder를 통해 custom한 것을 추가하면 gauges.add(Gauge.builder("my.datasource.jndi.export.name", jeusDataSourcePoolMetadata, ds -> ds.getJndiExportName().hashCode()) .description("JNDI Export Name of the datasource") .tags("name", beanName) .register(regi..

보호되어 있는 글입니다.

before this lecture we assumed prior distribution to be simple gaussian , but now we want something more complicate so we can map more complex manifold.it is hard to evaluate all the possible z, so in VAE we used encoder to find distribution z using q.instead of passing the z through these 2 NN and then sampling from a guassian, we directly transform the latent variable by applying a single dete..