Dharma-AI introduces a constraint-aware GPU allocator that improves GPU utilization by up to 33 percentage points and priority-weighted output by up to 105% compared to a FIFO scheduler, by reordering allocation decisions without changing hardware.
From the source
On identical hardware, running identical workloads, GPU utilization rose by as much as 33 percentage points, and priority-weighted output rose in every one of them, by as much as 105%.
huggingface.co