Viewing profile — DiabloD3

H.261 is from 1988. JPEG is from 1992.

They can't, unfortunately. Linux's drivers makes that happen, not ffmpeg; ffmpeg merely calls the API. Intel's own first party drivers simply follow the ACPI tables, Linux ignores …

See the end of https://news.ycombinator.com/item?id=49100144

It very much is actionable. You might not know this, but the world of software development existed before NPM and Github, and it continues to exist after them. You are not beholden…

Tell me where I can buy a car for $1k or $2k.

Every single analysis I've seen done by anyone has basically come to the same conclusion: assuming sane BF16 or Q8 model quant, and BF16 or Q8 KV context quant (ie, not intentional…

One of the biggest fixes I've seen is just getting rid of traditional sampling. But first, let me say something about quantization, just to get this out of the way. Like, lets say …

[flagged]

This is a problem with long context models. To put it as simple and as bluntly as possible: just because they claim you can use 1M tokens in your context doesn't mean its true and …

[flagged]

That is called a hallucination.

I don't understand the joke. Intel has already stated their deal with Nvidia, this came out in December. If you think there will be shipping Druid products, I guess you can find ou…

What GPU? Its usually Nvidia owners that complain about lackluster Wine/Proton performance.

Battlemage was still while Pat Gelsinger was CEO, and he was the only real champion of that product, understanding its place in Intel's overall strategy. He doesn't work there anym…

There will be no future Xe GPUs. Druid, the 4th generation, has been shelved entirely, and all consumer DGPU products, possibly _all_ DGPU products, have been killed for Celestial.…

A lot of games no longer run properly in Windows, and the only way to keep playing them is with Wine/Proton. Windows performance is also often worse than Wine/Proton's.

GPU clusters have, largely, no actual value. If anything, you might have to pay to have them disposed of, they don't really have any meaningful used eBay market outside of the rand…

Neat, can't wait to see a llama.cpp PR for this.

OnePlus basically already went under a few years back. They merged with Oppo, and ever since its just been rebranded Oppo phones... they're fine, they work, but they're not the mag…

Skip Samsung, they tend to not honor warranties and are ROM swap resistant. Google is okay for now (I recently got a Pixel 10, its fine, it can run Graphene). Next year Motorola fl…

Ironically, this is what people claim AI can do with a snap of the fingers. Should be real simple if the HN AI echochamber is right, right?

I love how people say things like "extension spaghetti", as if all other non-standard APIs have the same problem: hardware gets new features that people want to use from that API, …

Weird, most people have the exact opposite experience. Having to deal with closed source opaque poorly documented stacks sucks.

Weird, since the most used open source inference engine is faster on Vulkan on platforms that offer multiple options, with the sole exception being Nvidia, due to poor Nvidia drive…

Its easier to just get rid of your legacy code entirely and use Vulkan for compute, or have your compiler emit SPIR-V directly. No reason to tie yourself to Nvidia's moat.