Further, the performance improvements in 1.8 will probably make almost all apps faster anyway. Anyone counting nanoseconds needs to do their own benchmarking already to catch processor-specific regressions etc so probably exactly nobody will actually have a production regression from this.
I'm seeing about a 50% speedup. It depends what you mean by game changing, but you should certainly see if 3.11 is a drop in replacement for whatever you are doing.
The article has quite a few performance numbers in it. The short answer is that it's much, much faster but that we will continue to pursue improvements pretty much forever.
I think that's a very welcome improvement. With NVMes that go at 7 GB/s we're now at the point that it can be hard to do anything useful with the data fast enough.
So I think good acceleration for things like compression is going to be a big help.
I think it will be a pretty sizeable jump (100% growth?). I expect the next 0.8 release will make a lot of noise when they leave Handlebars behind and really ramp up the rendering engine side of things.
This is true! Although I'm also really excited at the potential speed (both for loading the model and token generation) of a 1B model for things like code completion.
This is one of the things that makes me most excited about Bun. It’s much faster for certain kinds of things like this, and I hope its focus on performance spurs a positive arms race of sorts.
reply