Vattila

Latest activity Postings Featured content About Trophies

• • Vattila reacted to Doug S's post in the thread Discussion Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025] with Like.

    Chiplets make more sense for Apple with a changing mix of needs. They had enough volume to justify separate dies for base, Pro and Max...

    Tuesday at 11:06 AM
  • Vattila reacted to Gideon's post in the thread Question Zen 6 Speculation Thread with Like.

    Whoa, a Zen Interview with Mike Clark by Casey Muratori (who is a really badass well informed developer btw )...

    Mar 27, 2025
  • Vattila reacted to Tuna-Fish's post in the thread Question Zen 6 Speculation Thread with Like.

    I think I know why it's that big. The MS requirement for the copilot+ sticker is 40 tops of sparse fp16, right? 8 CU of RDNA4 hits that...

    Mar 21, 2025
  • Vattila reacted to Tuna-Fish's post in the thread Question The AVX-512 thread with Like.

    The x86 ecosystem advisory group convened for the first time. I'd bet some money that all the user side people on it just spent their...

    Mar 19, 2025
  • Vattila reacted to DisEnchantment's post in the thread Discussion RDNA4 + CDNA3 Architectures Thread with Like.

    I am totally with you on this. I also am a bit disappointed with only 64CUs and 16GB VRAM. I could be in the minority of folks who love...

    Mar 16, 2025
  • Vattila reacted to igor_kavinski's post in the thread AI coding assistance discussion with Like.

    YES!!!!!

    Mar 16, 2025
  • Vattila reacted to MS_AT's post in the thread AI coding assistance discussion with Like.

    Well, you need to make sure you are interleaving numa nodes for best mem BW. Then check what MemBW you can achieve, divide by the model...

    Mar 16, 2025
  • Vattila reacted to igor_kavinski's post in the thread AI coding assistance discussion with Like.

    I decided to mess around with LM Studio on my 64C/128T Zen 2 server, just to see if having this many cores would help with performance...

    Mar 16, 2025
  • Vattila reacted to Red Squirrel's post in the thread AI coding assistance discussion with Like.

    I can see UI/UX being hard to do if you have no idea what you're doing while coding, but it can get you started on it. I have played...

    Mar 16, 2025
  • Vattila reacted to purbeast0's post in the thread AI coding assistance discussion with Like.

    I mean any feature that is needed and is specific to a specific web app is going to be pointless to send over to an AI model to try and...

    Mar 16, 2025
  • Vattila reacted to igor_kavinski's post in the thread AI coding assistance discussion with Like.

    If you can give me a prompt describing something that would be hard to do for a newbie human being in a few hours, I can run it by...

    Mar 16, 2025
  • Vattila reacted to purbeast0's post in the thread AI coding assistance discussion with Like.

    The only AI coding help I've ever used is when I do a google search for how to do something in python since I'm new to python and don't...

    Mar 16, 2025
  • Vattila reacted to Ken g6's post in the thread AI coding assistance discussion with Like.

    In the image generation space, which I've found more interesting, I've seen .safetensors, which are uncompressed, and .pt ("pickle...

    Mar 16, 2025
  • Vattila reacted to igor_kavinski's post in the thread AI coding assistance discussion with Like.

    The really crazy thing I learned is that you can create your own executable model and share it with friends and family. It just runs...

    Mar 16, 2025
  • Vattila reacted to igor_kavinski's post in the thread AI coding assistance discussion with Like.

    Yeah. gguf files. Kind of like a compressed document of trained knowledge.

    Mar 16, 2025

  Show older items
• Loading…
• Loading…
• Loading…
• Loading…