Running 1 mini-infer - PagedAttention KV-Cache & Prefix Studio 🚀 1 Interactive GPU PagedAttention block pool & prefix cache.
Running 1 RunsOnMine - Consumer Silicon LLM Serving Registry ⚡ 1 Empirical consumer GPU serving benchmarks on Dual T4 & 3050.
Running 1 sched-sim - LLM Serving Scheduler & Gantt Studio ⏱ 1 Discrete-event LLM scheduler simulator & Gantt player.
Running 1 infersize - LLM VRAM Capacity Planning CAD ⚡ 1 Pre-flight LLM VRAM sizing CAD & cloud TCO planner.
Running 1 QuantBench - Sub-Byte LLM Quantization Studio 🔬 1 Sub-byte quantization Pareto frontier & BitNet packer.