Show HN: Disaggregating GPU compute from CPU in ML job execution to scale GPUswoolyai.com·1 pts·medicis123·0
GPU-accelerated code on CPU-only environments -Remote GPU Kernel Executionyoutube.com·1 pts·medicis123·1
Sharing base model in GPU VRAM across multiple inference stack process [video]youtube.com·7 pts·medicis123·1
Sharing actual GPU core and VRAM utilization metrics for query on 10 LLM modelswoolyai.com·1 pts·medicis123·1
Show HN: WoolyAI-CUDA Abstraction Layer to Decouple Kernel Shader Exec on GPUwoolyai.com·4 pts·medicis123·0
Locally delivered and centrally managed macOS envs for privileged access setupveertu.com·1 pts·medicis123·0