Search papers, labs, and topics across Lattice.
4
0
8
4
Xronos is proposed, a collaborative fine-tuning framework for heterogeneous CPU edge devices that uses TP as its execution backbone and combines lightweight profiling with heterogeneity-aware tensor partitioning to reduce the straggler bottleneck.
The latency with respect to the resource dynamics of processing multiple requests and tasks concurrently is characterized and new optimization opportunities that exploit the resource dynamics of tasks are demonstrated: CPU-aware tool admission and task-aware CPU allocation.
GeoMesh is presented, a synchronous geo-distributed training framework for heterogeneous GPUs that balances per-worker workloads by assigning each GPU a suitable batch size and number of inner steps, so faster GPUs do more useful work instead of waiting.
OasisKV achieves up to 2.1x throughput gains in LLM inference while using significantly less memory, challenging the limits of current HBM constraints.
