Ivan Burazin
speaker
915 appearances
1 recordings
1 series
first heard May 2026
last heard 21 May
Ivan Burazin’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in May 2026 with 1.
Appearances
And we're all solving this in different ways.
So, yeah, I know specifically that like Neon had that issue as well.
Like how are we solving these spiky loads and things like that?
Because we talked about it.
And so the interesting thing for me to actually internalize was, yes, everyone that's building for agents first is going through this and we're all solving similar problems.
I mean, I put it up on the screen so people can look it up if they need to.
And yes, but they still have CPU and RAM allocation that you have to have in running.
And so CPU, RAM, you have to allocate that and have that ready.
And so there's basically two ways to do it.
One is you either over-provision and you can handle the bursts.
Or two, you basically have, I don't know if this is a term, just-in-time compute, which is like as your usage comes in, you can fire off requests for VMs or bare metals at other cloud providers and then get them up and running.
If your overflow like spillage or whatever.
Well, you might not.
That is a more cost-effective way to do it, but it's a slower way to do it.
Because basically what you have to do is you have to queue your requests, spin up these just-in-time compute, get it all ready, provision it, and then get your workload there.
And so if the time isn't important that much, that's fine, and you can do that.
But if your customer, and especially for, let's say, the RL training runs, the reason why a lot of people come to us is because GPUs are more expensive than CPUs, right?
So you want your GPU running at 100% the entire time.
And so when you're running runs on CPUs, when the CPU when the CPU cycle is like down and spinning up the next one, you want that to be instantaneous so that your GPU doesn't go down, right?
And if you then have to like go out and provision machines, you're essentially telling the GPU that it has to wait, and that's incurring our costs.
Showing 361–380 of 915 · page 19 of 46
← Previous
Next →