I'd have some other uses for RDMA between Macs.
I'd have some other uses for RDMA between Macs.
Of course, there was that one time they "upgraded" our building and forgot to re-plug my line to the router, but, oh well..
Overall, this seems like a super niche topic for HN. :)
Working > New
I haven't had the same problems this guy has, although I do believe his issues are real.
https://ntdotdev.wordpress.com/2025/09/06/tiny11-builder-sep...
FWIW, there's also the non-free JPEG-XS standard [1] which also claims very low latency [2] and might be a safer choice for commercial projects, given that there is a patent pool around it.
https://www.filmlight.ltd.uk/store/press_releases/filmlight-...
We currently use the IntoPIX CUDA encoder/decoder implementation, and SRT for the low-level transport.
You can definitely achieve end-to-end latencies <16ms over decent networks.
We have customers deploying their machines in data centres and using them in their post-production facilities in the centre of town, usually over a 10GbE link. But I've had others using 1GbE links between countries, running at higher compression ratios.
I can't possibly go back to non-Premium YouTube, and if they mess around with Premium I'll probably be moving on from YouTube.
There's a vinyl record label called Deep Jungle [0] which specialises in sourcing unreleased (or very limited pressings originally) 90s jungle/drum&bass straight from the artists - for a fair price.
Each release has a backstory often involving getting boxes of DATs down from the attic! The music is remastered with modern technology.
Demand is high (literally selling out within minutes!) as the label covers both older customers (who went raving in the 90s) and the younger generation exploring older music.
Everyone in DnB documentaries talks about going to Music House with DATs to get dubplates cut to play in the clubs later on that evening.
This would have been before CD-Rs were commonplace, early 90s.
This is still an early-stage project — it's not completed yet, and fabricating a custom chip would involve huge costs.
I'm a solo developer worked on this in my spare time, so FPGA was the most practical way to prove the core concepts and validate the architecture.
Longer term, I definitely see ASIC fabrication as the way to unlock PyXL’s full potential — but only once the use case is clear and the design is a little more mature.
I'd have some other uses for RDMA between Macs.
https://github.com/Anemll/mlx-rdma/commit/a901dbd3f9eeefc628...