davideom0414
Re:Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassi...
on Sunday February 22, 2026 @07:50AM (#47110592)
Really interesting experiment i should have done this before
Do you have numbers on effective throughput vs PCIe theoretical bandwidth?
I’m curious whether this is primarily latency-bound or bandwidth-bound in practice
Can some tell me??