ZML , a hot French AI startup endorsed by Turing Award winner Yann LeCun, has released inference -performance software that allows a variety of open-source large language models to run on a variety of chips — including Nvidia’s, AMD’s, Google’s TPU, Apple Metal and Intel Arc. With ZML/LLMD , the newly launched LLM inference server, the company’s ambition is to break existing silos and make different chips available for AI use cases at their maximum available speed, and sometimes faster, ZML founder Steeve Morin told TechCrunch. As AI becomes integrated into our work and everyday lives, optimizing inference — aka, the processing of prompts — has been outpacing model training in importance, but often feels patchy behind the scenes, with software and architecture barriers that lead to vendor lock-in, Morin said. TechCrunch AI is the main source layer for now, and the rest should be read as a signal that is still widening. The useful angle sits in the effect on user behavior, revenue flow, or how platforms compete for attention on screen.
What is happening now
ZML , a hot French AI startup endorsed by Turing Award winner Yann LeCun, has released inference -performance software that allows a variety of open-source large language models to run on a variety of chips — including Nvidia’s, AMD’s, Google’s TPU, Apple Metal and Intel Arc. TechCrunch AI form the main source layer behind the core facts in this piece. This is still a developing thread, so the useful part is knowing which source signals are hardening and which ones still need caution. On the internet and business side, the useful question is how much this change shifts user behavior, operating cost, or competitive pressure.
Where the sources line up
TechCrunch AI is the main source layer for now, and the rest should be read as a signal that is still widening. With ZML/LLMD , the newly launched LLM inference server, the company’s ambition is to break existing silos and make different chips available for AI use cases at their maximum available speed, and sometimes faster, ZML founder Steeve Morin told TechCrunch. TechCrunch AI form the main source layer behind the core facts in this piece.
The details worth keeping
As AI becomes integrated into our work and everyday lives, optimizing inference — aka, the processing of prompts — has been outpacing model training in importance, but often feels patchy behind the scenes, with software and architecture barriers that lead to vendor lock-in, Morin said. The useful angle sits in the effect on user behavior, revenue flow, or how platforms compete for attention on screen.
Why this matters most
The signal is strong enough to deserve attention, but it still needs to be read as something developing rather than fully settled. With 1 source layers on the table, the part worth reading most closely is where firm facts meet the market's early reaction. The promise of achieving peak performance across a variety of chips is a technological feat, but it could also be a market disruptor, amid mounting fears over AI-related costs.
What to watch next
The real follow-up is whether the story turns into measurable user, creator, or revenue impact. Patrick Tech Media will keep checking rollout speed, user reaction, and how TechCrunch AI update the next pieces. From 2 early signals, the piece keeps 1 references that are useful for locking the main details in place. That is why the useful reading move is not to stop at the headline, but to compare the promise, the workflow change, and the likely cost before deciding anything.