HN

Need help?
<- Back
AMD acquires Taalas to boost inference performance by etching models in silicon

AMD acquires Taalas to boost inference performance by etching models in silicon

itvision

Comments (279)

  • linzhangrun
    Thinking that five or six years from now, Fable-level intelligence could be provided at 100x the current speed... makes me feel lost. I cannot imagine what the future will look like.
  • LarsDu88
    I'm surprised neither OpenAI nor Anthropic made this move first. The Chinese open weight models are pulling ahead and commoditizing their value proposition.Baking models onto silicon would've been the next logical move to get a moat.Google is already doing this and has an experimental project on top of already having TPUs and cramming their quantized flash onto individual TPUs for inference.
  • whythismatters
  • yumraj
    Given the fast churn of the models, how does it work out?Won’t the silicon etched model already be 1 or more versions behind by the time the silicon comes out.Though if it’s cheap enough, there certainly can be a market for cheaper model inferences.
  • galaxyLogic
    I think the big news is that AMD is getting into memory-business so they won't be so dependent on Hynix and what have you. Memory is the bottleneck currently.
  • mNovak
    What I like about this, is that it significantly increases the probability of a sci-fi scenario where you're picking up a hot chip on the black market; rumor has it, Mythos 9 weights baked in...
  • msteffen
    This is neat but IMO a little crazy.Something I personally haven’t seen much of, in all the discussions of model benchmarks and AI breakthroughs, is a distinction between “peak performance” and “reliable performance”. The “peak performance” of frontier models is very high: they’re solving open math problems, analyzing large codebases, etc. But my subjective impression is that “reliable performance” is mid at best: out of 100 random questions I might think to ask, it’s likely to say something wrong or stupid a handful of times at least.I think there’s inherent tension between the two: the more a model reaches or outright hallucinates, the more likely it is to come up with tricky, subtle solutions to problems (I think people are somewhat like this too: Terry Tao’s brother is nonverbal, Jim Watson’s son has severe schizophrenia, etc). But then the less likely it is to generate a sensible email reply.I use models all the time for coding, but I would not let one take over my daily correspondence. If the idea here is to run frontier models at high speed in data centers, that could be useful (the speed would be cool), but I’d be surprised if the cost of that hardware churn is worth it to frontier labs. But if the idea is to turn this into a chip that goes in your phone as some kind of routine, low-power inference thing…taking something too kooky to be relied on and baking it into your phone’s hardware like that doesn’t make sense to me.
  • A_D_E_P_T
    This is probably a win-win. The team gets paid, and we get greater assurance that their best ideas and architectures -- which are truly impressive -- are going to see the light of day in actual products.
  • badatnames
    Well so much for that dream.Guess we can look forward to picking these up ex-enterprise on ebay for under $5k a pop in a decade or two
  • mikeayles
    AMD could have saved their money and used their own hardware! I've got a language model doing 60k tok/s on AMD hardware already, a Xilinx Kria K26 SOM, with the weights baked into URAM/BRAM with zero DRAM in the token loop. Same thesis as Taalas: single-stream decode is bandwidth bound, so stop fetching weights from far away.Caveats stacked high, obviously. It's 3.16M parameters (tinystories, and I also have a kevin-speak lemmatised version), the tokens are characters, and the 60k record is 16 streams that each remember exactly one token of context, so it's blisteringly fast at saying nothing. The honest build with full context and KV caching still does ~19k tok/s on one stream though.I keep messing with the blogpost with the live demo, but I'm planning on flipping it to live in the next day or two
  • andix
    It would be quite ironic if this technology would render all those AI data centers practically useless. If the next step are just a much smaller amount of expensive chips, and the bottleneck becomes manufacturing those chips fast. Not building huge data centers and fighting for electrical power.
  • OddMerlin
    Congrats to the Taalas gang.
  • sgc
    What does it take to go from here to a model on a pcie card or an m.2 card, so I can plug one into my workstation / laptop? Will 'intelligence' become much like a gpu, where most people just live with the performance of whatever they have installed, outside large companies that must have cutting edge, or prosumers that have a incrementally better version than the masses?Are we a couple years away, a decade away, or something else?
  • concraper
    A massive L for Canada
  • proxysna
    Really hoped to see their hw out in the wild one day
  • redox99
    Is there any LLM from exactly one year ago that would be worth running?In Aug 2025 you had- OpenAI o3- Opus 4.1- Gemini 2.5 Pro- Grok 4Even if those were almost free to run, you'd be way better off with Deepseek flash 0731 or GPT 5.6 Luna, which already are almost free.Other than for things where the t/s are critical, it seems like a bad idea to etch a model into silicon.
  • galaxyLogic
    "... the chip serve Meta’s Llama 3.1 8B at a blistering 16,960 tokens a second — when announced last February, that was 48x faster than Nvidia's GPUs and 8.5x faster than Cerebras' accelerators. "
  • nojs
    Can anyone comment on the economics and likely turnaround times of this process, when it’s more mature?Would it be realistic for a frontier lab to deploy this or would the turnaround time mean the model is always too out of date?Assuming the weights and architecture are eventually stable, how much cheaper would this end up being?
  • preommr
    People are missing the point if they think this is useless because frontier models keep changing every few months.We really, really need better secondary models that can do things fast and do them cheaply for lots of dumb tasks. Not only because it can be used as sub agents by frontier models, but also because it can be like a universal grease for all kinds of software.I've got an app I am building and I don't want to tie myself with frontier models because I'll never be able to beat openai/anthropic. I just want a simple, cheap, instantaneous model that can just go through my documentation and tell the user what to do next and how to integrate with whatever ai subscription they have.
  • syntaxing
    Honestly, this is starting to make more and more sense. SOTA models are starting to converge to certain architecture and capabilities. I wouldn’t be surprised we end up with a base model ASIC + “fine tune” card where it’s a physical LoRA style adapter.
  • bhouston
    Toronto Canada startup btw.
  • redmoonx
    It obviously won’t be continuous delivery but could make sense if the lifecycle of a model (train, deploy, iterate (meaningfully) is about 1-2 years. In that case it fits nicely in the “this year’s model” already established with cars, phones, etc.
  • MarkWayneNewton
    While this design is self-limiting I think its a good approach. It doesn't take an entirely new architecture or infinite memory to produce significant performance improvement.
  • laweijfmvo
    I’ve been using Gemma as my default (via Kagi) because it’s served on Cerebas hardware. The speed is honestly a game changer for day to day queries.
  • ggm
    Field reprogrammable, it's an FPGA on steroids. Field upgradable.Burnt in, it needs a zif socket and easy access in every car, aircraft, a pull out slot in a phone, or it's new era planned obselescence.
  • drob518
    So, Kimi K3 in silicon sometime soon?
  • roughly
    How's that jive with the fact that they're introducing a new model every other week?
  • yousif_123123
    If things like this get traction, will we need all the datacenters?
  • jackdoe
    Can you imagine in few years getting Fable level intelligence at 20k tokens per second?"You are not prepared" --Illidan Stormrage
  • rvz
    Didn't even give them a chance to launch the hardware.
  • jauntywundrkind
    Core rope memory is back baby!Enjoying the Ian Cutress / TechTechPotato video on Taalas. Some ok good technical details on the tech, and some good insider baseball, whose who stuff. (What a treasure having tech discussions like this about.) https://youtu.be/3MKRjt59hh4
  • tecoholic
    With web search and tool call a decent current generation model at the speed of the chatjimmy could do a lot. People saying it would be out of date are missing the point. It’s not going to make much sense for frontier companies that’s chasing the SOTA. But for a lot of business use cases if someone can put GLM 5.2 and sell it as a box, it would make so much sense.My partner has been asking for a “completely private” model for doing research and shifting through volumes of data that can’t leave the office and $$$ for the current hardware makes no sense. It would be an easy sell if someone walks in with a black box that contains “ChatGPT”.
  • bob1029
    I feel like NAND process tech could become useful at solving some of these problems. A GPU where you can update the weights a few thousand times may be sufficient.
  • api
    I've had an endgame idea in mind for a while.Models, probably first open weight ones like Kimi K3 class, are etched into silicon like this and sold as cartridges almost like old school game cartridges.You buy a USB-C dongle that the cartridge goes into, or for data centers you have PCI cards that take these in slots.
  • andrewvl
    It must be a “super model”. What will be if new model released? New chips?
  • ycui7
    so qwen3.x-27b on hardware? or better deepseek-v4-flash on hardware .
  • ur-whale
    Yeah, so https://chatjimmy.ai/ ... the model is crap, but the speed is amazing. Worth checking out.
  • fellowniusmonk
    Token quantity will have a quality all its own.
  • walrus01
    Imagine the size of chip needed to 'etch' something like Qwen 3.6 27B in size.
  • cubefox
    > At 20 billion parameters per chip, you’d need just 50 accelerators to support a trillion-parameter modelI don't see any evidence that this is possible. From my understanding, the whole model needs to be on a single chip. Which rules out any popular frontier models with several trillions of parameters. Even smaller sub-frontier models have hundreds of millions of parameters, so these would be ruled out as well.
  • moralestapia
    Taalas is just a phenomenal startup from Toronto. My dearest congratulations to the founders.Edit: Lol, downvotes? Stay jelly, meanwhile Talas goes brrr.