CUDA 13.4 GPU Fractions: The Enforcement Gap in Kubernetes
Why a scheduler's GPU-memory reservation is not an enforced limit, how CUDA 13.4 and GPU Fractioning close the gap, and what to test before multi-tenant rollout.
Research · Guides · Explainers
Independent AI research & technical writing
The RAMGPT library / 4 articles
Choose CPUs, GPUs, memory, and storage for AI workloads.
Why a scheduler's GPU-memory reservation is not an enforced limit, how CUDA 13.4 and GPU Fractioning close the gap, and what to test before multi-tenant rollout.
A new llama.cpp CUDA PR targets duplicate activation quantization and intermediate FP32 traffic in dense Q4_K MLP prefill, with contributor-reported gains from 4.1% to 14.7%.
A new llama.cpp CUDA patch shows that Blackwell NVFP4 prefill was limited by tile delivery, barriers, and register pressure—not simply tensor-core arithmetic.
See which model sizes fit 8, 12, 16, 24, 48, and 80 GB GPUs, then account for quantization, KV cache, context length, and runtime overhead.