GPU Time‑Slicing doubles LLM agent tail latency on a $150 GTX 1080
When two LLM agents share a single low‑cost GTX 1080 via Kubernetes CUDA time‑slicing, average throughput stays flat but the latency‑sensitive agent’s p99 jumps by 66 % and jitter rises 67 %. The hidden tail cost means dashboards based on averages can miss deadline breaches, warning that cheap GPU sharing isn’t free.