Stories by medicis123

A New Approach to GPU Sharing: Deterministic, SLA-Based GPU Kernel Scheduling

Show HN: Disaggregating GPU compute from CPU in ML job execution to scale GPUs

Show HN: Run PyTorch on CPU boxes, offload kernels to remote GPUs

Running Nvidia CUDA PyTorch container project/pipelines on AMD with no changes

GPU-accelerated code on CPU-only environments -Remote GPU Kernel Execution

Sharing base model in GPU VRAM across multiple inference stack process [video]

Sharing actual GPU core and VRAM utilization metrics for query on 10 LLM models

Show HN: WoolyAI-CUDA Abstraction Layer to Decouple Kernel Shader Exec on GPU

Locally delivered and centrally managed macOS envs for privileged access setup

Shopify scaling iOS CI with Anka