Axelera AI is excited for @Supercomputing 2024 in Atlanta this November! Join us at Hall B – 4623 from Nov 17-22 at the Georgia World Congress Center. Meet our team and discover how our Metis platform can accelerate your AI solutions. https://
sc24.supercomputing.org
#AI #HPC #SC24
COMPUTING
-
Axelera AI Showcases Metis Platform at Supercomputing 2024
By
–
-
Microsoft Struggles to Secure Sufficient Power for AI Ambitions
By
–
Microsoft apparently cannot get enough power for AI Twilio’s peek into 2025 gives reason to hope for double-digit revenue growth, Meta’s spending is once again a cause for concern, and Microsoft is having a hard time getting enough power to fuel its AI ambitions. $MSFT $TWLO
-
VRAM Requirements for AI Models Across Hardware Architectures
By
–
It should work on CPU/ CUDA/ MPS across backends, w.r.t hardware requirements: 1B should take roughly 2GB VRAM to load in fp16/ bf16.
600M should take 1.2 GB VRAM
350M – ~700MB VRAM
125 – ~250MB VRAM Ofcourse at lower quants Q4/ Q8 you reduce this even further. -
Tiny AI Models Running on Everyday Devices
By
–
Models so smol that thay'd even run on your toaster!
-
Building Large-Scale Clusters to Train and Release Llama
By
–
its super fun to build very very large clusters, train llama on them, and release it for y'all to enjoy — and talk in great detail about how we did it!
It's also really fun to partner with @Ahmad_Al_Dahle in creating this disruptive chaos Join us, there's lots of work to do! -
Custom Silicon Development Accelerates with Reduced Costs
By
–
“We’re going to bring down the time-to-market for new custom silicon, and the cost,” @DavidBennett__ in @the_logic Read more here –>
-
Accelerator Support: System Dependencies and Binary Storage Challenges
By
–
there are two problems, you've identified both:
1. accelerator support involves system package and driver version resolution that we didn't have to meaningfully confront with CPUs (CPUs just had to deal with arch)
2. accelerator binaries are large — so we had to move to s3 -
PyTorch modernizes accelerator support with improved uv integration
By
–
we're willing to fix it to work better with uv (which is fantastic) cc: @_seemethere I think PyTorch was forced to solve the accelerator support problem before Python packaging was ready for it, so we solved it as best as we can — but we're willing to move to a better world if
-
AI Inference Market Reaches $102B by 2027
By
–
AI inference – running AI apps post-training – is set to reach a market value of $102B by 2027. As @beach66 says: "Where that inference is going to be deployed is everywhere." @Reuters
' @chernandburn details our solutions made to meet this growing demand.
