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

[delayed]

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

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.

The demo: https://chatjimmy.ai/

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.

Toronto Canada startup btw.

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.

Really hoped to see their hw out in the wild one day

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

so qwen3.x-27b on hardware? or better deepseek-v4-flash on hardware .

Didn't even give them a chance to launch the hardware.