logoalt Hacker News

akiselevlast Monday at 5:59 PM2 repliesview on HN

The weights are in SRAM, so the LLM architecture is burned in but the weights can be updated.


Replies

Tuna-Fishlast Monday at 9:55 PM

Taalas only uses SRAM for the KV cache and the activations, the weights are in mask rom in the metal layers.

If they designed this right, it means that once they have a model, so long as they keep the hyperparameters fixed they can change the weights much faster than it takes to spin up a completely new chip, essentially at a cost of doing a minor revision.

show 2 replies
hedgehoglast Monday at 7:10 PM

No the weights are in the metal layers, they cannot be updated.

show 1 reply