Tag
The author demonstrates forcing AMD MI50 GPUs to work with ROCm 6.4.3 and building a Vulkan-based neural network training stack, challenging the consensus on legacy hardware support.
Describes running the GLM-5.2 model with 4-bit quantization at 12.2 tokens per second on a cluster of 16 AMD MI50 GPUs using llama.cpp's RPC, achieving coherent long-form generation at 10.7k context.
A user benchmarks AMD MI50 GPUs across different PCIe configurations on an older X99 motherboard, comparing direct PCIe connections vs using a PEX8749 switch. Results show minimal performance difference with slight improvement in token generation speed.