Thank you, It would be a great help if you can share the Jupyter notebook with the profiler configurations.
@acasualdatascientist543 жыл бұрын
I second this
@retfordb3 жыл бұрын
is there any support for utilizing pre-compiled kernels for larger shapes through multiple invocations while compiling a new kernel in the background? Or any other kind of intelligence around dynamic recompilation?
@biygi9178 Жыл бұрын
ផផ
@bensouthall26125 ай бұрын
Is that pseudocode of the Add function a real language? Or just an example?
@TeoZarkopafilis3 жыл бұрын
Are the slides available?
@mathieswedler2 жыл бұрын
I tried running my model with jit compile=True, I got constantly 100% GPU utilization and the terminal stated the graph is using XLA. However, training was faster (and around 80% GPU utilization) WITHOUT XLA. How is that possible? What did I do wrong?
@kyrgyzsanjar10 ай бұрын
did you figure out the reason?
@trihasta4229 Жыл бұрын
var=i.0
@WillFalcon3 жыл бұрын
Я тоже по-английски умею говорить, но нахера ты это выложил?