Search results

  1. A

    SXM2 over PCIe

    Please share what you chose for voice-to-text implementation.
  2. A

    SXM2 over PCIe

    Thanks for the reply, I'll be careful with the raiser. Even without it, my board sometimes goes into x8 mode. About larger models (Inference), as I understand it, it's better to run it on the CPU if there's not enough space for the GPU. Otherwise, the PCIe (even Gen5) will be a bottleneck and be...
  3. A

    SXM2 over PCIe

    Inference scenario: Choose a single 32GB V100 If you work with large models or datasets that won't fit in 16GB. 3-10x tokens per second compared with 2x 16GB V100. Choose two 16GB V100s If your models fit in 16GB and your primary constraint is parallelism. 2x request per second compared with...
  4. A

    SXM2 over PCIe

    How are you getting on? Have you tried it without riser? What was the problem? I have one 16GB card that works fine at x16. I'm waiting for another 32GB card and another PCIe adapter with three fan outputs. What length of riser did you use?
Top Bottom