HN user

searealist

513 karma
Posts2
Comments507
View on HN

MTP can give you small batches, but it is still WAY smaller than the batches you can get with prefill, which is limited only by the number of input tokens you have (but has diminishing returns on performance).

But:

1) It still makes no sense to upload the weights to the GPU with MTP as you are still bottlenecked by the weight upload.

2) I'm not sure MTP helps much with MoE models.

There are two phases to LLMs:

1) prefill

2) decode

For prefill, you are compute bound, and it is trivial to batch multiple input tokens together. When using cpu offload, software like llama.cpp will batch weight uploads with tokens that need those weights and perform work on the GPU. It works very well. With a large batch size and pcie5 you can get prefill speeds close to having all weights on the GPU.

For decode, you are bandwidth bound, and it is difficult to batch multiple output tokens together. There is no benefit to sending your weights to the GPU because even if it internally has insane bandwidth, you are still bottlenecked by system RAM (and adding a pcie5 upload would bottleneck it further). This is the number people usually talk about when they say they are getting a certain tk/s.

Kramnik ((ab)using his status as a former world champion) accused several other top level players to the point that one of them committed suicide.

There is no evidence of suicide, and he had multiple drugs in his system when he died.

he probably did cheat in this particular game

This is a fringe opinion at this point in time, even though it was obvious he did not cheat on day 1.

Sindorov, who won the candidates, and will be playing for the world championship, has also had accounts banned on chess.com for (presumably) cheating as a teenager. Do you think it would be ok if a large part of the chess world conspired to keep him out of tournaments. Do you think it would be ok if the world made jokes that he cheated using a sex toy? Do you think it would be ok for the largest youtube chess channel (GothamChess) to publish a video titled "Chess cheating device" featuring a thumbnail showing his face next to a butt plug? And all this while he was 19?

What happened to Hans is FAR worse than anything Kramnik did. But maybe you think it's ok because you find him to be an asshole?

Just to clarify, many third wave shops do serve medium and dark roasts. My point is that third wave coffee shops often call a roast dark when they are actually medium or light. Additionally, I think only light roasts really qualify as third wave.

Most of the coffees you listed look like actual dark roasts.

"Full City Roast" with "lemon zest" in the flavor notes raises some red flags for me. Indeed, from the reviews: "Yum! I don't like dark roasts, and this is not a dark roast which is why I liked it. Lots of chocolate. Very smooth, not bitterness, a hint of fruit as it cools. I really enjoyed drinking this."

"Imunika Black" might also be an exception: the "blackberry" tasting note makes me think it isn't very dark.

I see more with citrus or other fruity descriptions, and I doubt those are dark roasts either.

This is actually a perfect example. I agree that you can find dark roasts at some third-wave shops, but they are _not_ third-wave coffee.

Our premier dark roast is a nod to the old style of roasting which is still favored throughout the world

In this case, they even go out of their way to disqualify it as a third-wave roast.

Here the first sentence of Third-wave coffee's wikipedia page:

Third-wave coffee is a term primarily in the United States coffee industry emphasizing higher quality, single-origin farms and light roast to bring out distinctive flavors.

I also strongly suspect your definition of "decently dark" is still below a medium roast. If not, I would be interested if you could cite a "decently dark" roast you have tried from a third-wave coffee shop.

The thing is, acceptance at these elite universities is _highly_ correlated with academic performance. It’s just that different racial groups are admitted in different ranges. You won’t find a single Asian at Harvard at or below the median Black SAT score. The range to be accepted as an Asian is also higher than Whites, which is higher than Latinos, which is higher than Blacks. How can you possibly explain this if it’s not a quota system based on race?