Mingshu Zhai
where else to find them
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
all 13 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| mTuner: Accelerating Parameter-Efficient Fine-Tuning on Multi-GPU Servers with... | USENIX ATC '25 | 2025-07-07 |
mTuner implements an Elastic Tensor abstraction that exposes four tunable operations — gather, discard, execute, checkpoint — and a one‑time schedule search to… | ||
| QFactory: Accelerating Quantized Large Language Model Serving with Qtile Graphs | USENIX ATC '25 | 2025-07-07 |
QFactory is a compilation framework that generates fused quantized kernels by deferring dequantization, representing quantized tensors with a Qtile-graph… | ||
| PUZZLE: Efficiently Aligning Large Language Models through Light-Weight Context... | USENIX ATC 2024 | 2024-07-10 |
PUZZLE implements a two-dimensional model-orchestration system that reduces context-switch overhead during RLHF by adding time-sharing within stages and a… | ||
| SmartMoE: Efficiently Training Sparsely-Activated Models through Combiningand... | USENIX ATC '23 | 2023-07-10 |
SmartMoE is an automatic system that combines two-stage parallelization (offline pool construction + online selection) with a data-sensitive performance model… | ||
| nothing matches | ||