ChatJimmy is a much smaller model and, AFAIK, has no reasoning capability. Absolutely insane raw speed, like a supercar, while Sol is more like a freight truck.
> At such output speed, I wouldn’t expect reasoning.
As the sibling comment to yours mentioned, if they had a reasoning model “hardware-ified” onto a custom chip (as is their plan for IIRC this or next year, a new ASIC), it’d output fast decode speeds for the regular output as well as reasoning sections. Both would be ≈equally fast.
Yeah, I thought reasoning was literally just chain of thought in the output token stream, with the model itself adding delimiters to indicate what part of the output is internal reasoning, and what part is an answer to the user. Is that wrong?
No, as the sibling comment mentioned, your understanding was correct there.
What’s more, the only technical difference in speeds could be, and likely also is with the HC1 chip, between prefill (prompt processing) and decode (text generation) speeds. I don’t know whether it’s the case with Taalas’ chip, but in the “software-based” LLMs we typically see and use so far, those two stages hit different parts of a computer (processing/compute-bound vs. memory/bandwidth-bound).
Haha, at first I thought you meant that the knowledge of the existence of an LLM that’s so fast is terrible because it’s ruined every other LLM for you!
Apparently they baked the Llama 3.1 8B model weights [0] into silicon (the actual hardware is called Taalas HC1).
I guess for the trillion parameter models this would not scale due to cost? Imagine buying GPT 6 in the form of a PCI-E card, pulling these speeds, with up to 120 cct agent sessions. It'd be beyond wild.
[0] the weights are also using some cut down small format, but HC2 will have regular FP4 supposedly, and support for 20B params on one die
> Never heard of it before, that's fucking insane.
They've been acquired by AMD. Those saying the model sucks are completely missing the point: it was a proof-of-concept.
The question is: what happens to a model like Anthropic's Fable 5 that does, what, 70 tokens/s (and requires lots of output tokens) when the latest open-weights model is etched on silicon and does 14 000 tokens/s?
Shall the better model still have the upper hand or will the raw speed compensate?
Shall the better model still have
the upper hand or will the raw speed
compensate?
At 14,000 tokens/sec there's just so much ridiculous stuff that might be possible. Let's assume that this POC proves they can take the next step, and can eventually etch a capable ~27B model into silicon. Let's call it Fred.
Ralph loops automatically get real real interesting again. 200x the iteration speed. This is such a clear win I feel like there's hardly anything to talk about. Instead of one stubborn iterating idiot, you could have dozens of idiots competing in parallel, genetic algorithm style.
The other common orchestration pattern I see is "big model for planning, small parallel subagents implementing, big model reviewing" Today it's Sol dispatching a handful of Luna subagents. Tomorrow maybe it's Sol dispatching as many Fred subagents as it could possibly want.
But what patterns have we not even thought about yet in a world where subagents are 200x faster/cheaper?
What if instead of dispatching single Haiku/Luna/etc subagents, we dispatched "teams" of Fred agents? Maybe each team is 8 Freds. Five come up with competing ideas and the other three vote on a winner.
Or what if they were heterogenous teams? One Luna and a bunch of Freds.
What if instead of a two-tier orchestration system (Sol->Luna) it was three-tier or n-tier? (Sol->Luna->Fred->...Fred)
Those ideas overlap a bit, and crazy shit like Gas Town has already explored even wilder ideas I guess. But man, 14000 tk/sec opens up so much stuff.
At 14,000t/s that's effectively a motor cortex for an android, you no longer need to train the robot to walk, it has a general idea for how to walk (baked into the 1b model), and then just corrects based on sensor input, in real time.
I still personally think that a heavy lean into MoE will be better for that sort of thing. Our brains are subdivided into large parts but I'm sure (and I'm not a brain scientist) that those parts can be subdivided even further into systems that run at various frequencies and latencies depending on what they're used for.
I was thinking about it the other day actually. How our brains evolved structure. I imagine it was purely just down to evolution adding/clustering additional cells around the areas where additional cells were needed. And after long enough a natural brain architecture emerged.
Makes me wonder if we're on the right track with transformer architecture/attention but if it'd be more effective on a larger scale, like MoE with a billion "experts".
That seems promising to me too, although, the thing I've always read is that you can't make the "experts" too narrow. Even if you had a "coding expert" it has to know a lot more than coding - if you tell it to make an online store it needs to parse your language, understand the internet, what a "store" is in this context, etc.
I am not a primary source, probably not even a secondary or tertiary source, so take this with all the grains of salt.
Oh for sure, but I think generally multiple experts are selected in an MoE pass for a token, so presumably it'd select programming related ones as well as general knowledge/language.
Only problem would be the routing layer works on the previous token as far as I understand so it might need more informational depth than just "a token" to select experts, I suppose in the same way attention works.
I wish I had the GPUs to run those sorts of experiments ha ha.
ChatJimmy is a much smaller model and, AFAIK, has no reasoning capability. Absolutely insane raw speed, like a supercar, while Sol is more like a freight truck.
At such output speed, I wouldn’t expect reasoning. (But I didn’t know it, thanks.)
700 TPS with reasoning is awesome and it speeds things up.
Cerebras as public traded company is worth keeping an eye what they produce.
> At such output speed, I wouldn’t expect reasoning.
As the sibling comment to yours mentioned, if they had a reasoning model “hardware-ified” onto a custom chip (as is their plan for IIRC this or next year, a new ASIC), it’d output fast decode speeds for the regular output as well as reasoning sections. Both would be ≈equally fast.
Yeah, I thought reasoning was literally just chain of thought in the output token stream, with the model itself adding delimiters to indicate what part of the output is internal reasoning, and what part is an answer to the user. Is that wrong?
No, as the sibling comment mentioned, your understanding was correct there.
What’s more, the only technical difference in speeds could be, and likely also is with the HC1 chip, between prefill (prompt processing) and decode (text generation) speeds. I don’t know whether it’s the case with Taalas’ chip, but in the “software-based” LLMs we typically see and use so far, those two stages hit different parts of a computer (processing/compute-bound vs. memory/bandwidth-bound).
You are right, reasoning is unrelated to tokens per second.
Anything will be fast if you etch it straight to silicon
The knowledge of ChatJimmy is terrible. Even Qwen on my iPhone is better.
ChatJimmy isn't a model, it's Llama 3.1 8B hardwired into silicon. The point isn't to be a good llm, but to showcase the speedup that's possible
well, yeah, it's based on a 2+ year old tiny model. It's very much an alpha proof of concept that they can perma-bake an LLM into silicon.
https://huggingface.co/meta-llama/Llama-3.1-8B
Haha, at first I thought you meant that the knowledge of the existence of an LLM that’s so fast is terrible because it’s ruined every other LLM for you!
Never heard of it before, that's fucking insane.
Apparently they baked the Llama 3.1 8B model weights [0] into silicon (the actual hardware is called Taalas HC1).
I guess for the trillion parameter models this would not scale due to cost? Imagine buying GPT 6 in the form of a PCI-E card, pulling these speeds, with up to 120 cct agent sessions. It'd be beyond wild.
[0] the weights are also using some cut down small format, but HC2 will have regular FP4 supposedly, and support for 20B params on one die
> Never heard of it before, that's fucking insane.
They've been acquired by AMD. Those saying the model sucks are completely missing the point: it was a proof-of-concept.
The question is: what happens to a model like Anthropic's Fable 5 that does, what, 70 tokens/s (and requires lots of output tokens) when the latest open-weights model is etched on silicon and does 14 000 tokens/s?
Shall the better model still have the upper hand or will the raw speed compensate?
Ralph loops automatically get real real interesting again. 200x the iteration speed. This is such a clear win I feel like there's hardly anything to talk about. Instead of one stubborn iterating idiot, you could have dozens of idiots competing in parallel, genetic algorithm style.
The other common orchestration pattern I see is "big model for planning, small parallel subagents implementing, big model reviewing" Today it's Sol dispatching a handful of Luna subagents. Tomorrow maybe it's Sol dispatching as many Fred subagents as it could possibly want.
But what patterns have we not even thought about yet in a world where subagents are 200x faster/cheaper?
What if instead of dispatching single Haiku/Luna/etc subagents, we dispatched "teams" of Fred agents? Maybe each team is 8 Freds. Five come up with competing ideas and the other three vote on a winner.
Or what if they were heterogenous teams? One Luna and a bunch of Freds.
What if instead of a two-tier orchestration system (Sol->Luna) it was three-tier or n-tier? (Sol->Luna->Fred->...Fred)
Those ideas overlap a bit, and crazy shit like Gas Town has already explored even wilder ideas I guess. But man, 14000 tk/sec opens up so much stuff.
At 14,000t/s that's effectively a motor cortex for an android, you no longer need to train the robot to walk, it has a general idea for how to walk (baked into the 1b model), and then just corrects based on sensor input, in real time.
I still personally think that a heavy lean into MoE will be better for that sort of thing. Our brains are subdivided into large parts but I'm sure (and I'm not a brain scientist) that those parts can be subdivided even further into systems that run at various frequencies and latencies depending on what they're used for.
I was thinking about it the other day actually. How our brains evolved structure. I imagine it was purely just down to evolution adding/clustering additional cells around the areas where additional cells were needed. And after long enough a natural brain architecture emerged.
Makes me wonder if we're on the right track with transformer architecture/attention but if it'd be more effective on a larger scale, like MoE with a billion "experts".
I am not a primary source, probably not even a secondary or tertiary source, so take this with all the grains of salt.
Oh for sure, but I think generally multiple experts are selected in an MoE pass for a token, so presumably it'd select programming related ones as well as general knowledge/language.
Only problem would be the routing layer works on the previous token as far as I understand so it might need more informational depth than just "a token" to select experts, I suppose in the same way attention works.
I wish I had the GPUs to run those sorts of experiments ha ha.
Yes, imho 14k TPS is just a beginning.
This Gas Town? https://github.com/gastownhall/gastown
Unfortunately AMD bought them, so I don't think we will get to see another release from them.
Aha, thanks, that’s fresh; press release is from Aug 6
https://ir.amd.com/news-events/press-releases/detail/1296/am...