Asan!

All big companies pull these kind of tricks. Another variation is to retire the old setting and introduce a new one with a deceptive name that is default on again.

Don't give them any ideas. Trump hates Ukraine ever since their refusal to back up his bullshit claims.

And the aftereffects last for months. Gas stations can't simply switch their red dyed diesel tanks for regular diesel tanks because then everybody tanking from that reservoir will potentially end up fined. The detection gear is so sensitive that if you used red dyed diesel once and then half a year of regular you could still prove it.

The humor in those is so perfect. "Have you seen this chicken?"

"Good grief, it's you!"

I find it extremely funny the meta idea that the author is steps ahead of you anticipating how you are going to react to the gag.

"Oh, it's you!" is also one of my favourite gags not only because Wallace is surprised but because everyone else also is. In a short silly message it was able to communicate the intent Feathers Graw has and to put the viewers in it

Yeah it's an incredibly good tie off to a complex joke and I think about it a lot. Really the whole thing is just a masterpiece.

Again!

Why is it up to other countries to solve your domestic issues?

The llama.cpp guys don't get nearly enough credit for their work. Though the quality of the codebase is dropping over time, it is still quite high compared to most of the alternatives, and it is still one of the most stable ways to run a large variety of models.

Definitely worth looking at if you have only a single 5090 is ninfer, and various hardware specific forks (3090, 4090).

The problem is that with diverse hardware such a set of defaults is much harder to make. You get this matrix of possibilities: gpu, VRAM and memory configurations and then the model axis. This leads to way too many options. The better alternative would be to have the runner self-benchmark what the best settings are given that it already has access to that one particular configuration.

With llama.cpp once you have the model + the runner on the same box you have from 1 ... 40+ configurations of GPUs (depending on how many gpus you have and how many sub-classes of GPUs) for basic options that will load the model. Then you can start multiplying by different batch sizes (1024, 4096, 8192), CPU thread counts (4, 8, 16), tensor splits (this can get really hairy), P2P enabled/disabled, various caching options, speculative decoding options and so on.

The effect is that you can easily spend a day or more benchmarking. On first run of a new model the software should figure this out by itself.

llama-bench is next to useless for this purpose.

3090 and 4090 are amazing value for the money on the second hand market. 5090's are sold for more than they were worth when they were new and new ones are ridiculously priced.