Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
DynaSpa
Published:
DynaSpa is a dynamic sparse GPU execution framework for convolution and attention. It selects custom GPU kernel variants for input-dependent sparsity patterns and uses sparsity-aware tiling to group irregular active regions into GPU-friendly work tiles, improving shared-memory/L1 reuse and reducing global-memory traffic. The system achieves up to 7.8× operator speedup.
DAF
Published:
DAF is a memory-efficient DNN training runtime that dynamically adjusts activation precision according to runtime importance. Kernel fusion reduces quantization and memory-movement overhead, while a page-based memory manager supports variable-sized quantized activations and reduces training memory usage by up to 22.9×.
TokenFlow
Published:
TokenFlow is a responsive LLM serving system with buffer-aware preemptive scheduling built on SGLang. Its scheduler tracks each request’s buffered tokens and target consumption rate, pausing requests that are overproducing and resuming those running low to maintain responsive streaming under bursty workloads. Proactive KV cache migration between GPU and CPU memory overlaps cache movement with computation, improving effective throughput by up to 82.5% and reducing P99 time to first token by up to 80.2%.
LeanStream
Published:
LeanStream is a GPU-centric LLM inference runtime for models whose weights do not fit in GPU memory. It continuously refines weight priorities from partial GPU results, asynchronously streams high-priority weights from storage, and executes loaded weights as they arrive to overlap I/O with computation. On edge SoCs, fine-grained CPU-GPU coordination through unified memory and custom GPU kernels delivers up to 2.1× higher token-generation throughput and 7.5× lower memory usage. A server-side extension using persistent GPU kernels for remote weight streaming is in development.
publications
ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive Inference
Published in ACM Multimedia 2023, 2023
DynaSpa: Exploiting Spatial Sparsity for Efficient Dynamic DNN Inference on Devices
Published in SenSys 2024, 2024
DAF: An Efficient End-to-End Dynamic Activation Framework for On-Device DNN Training
Published in MobiSys 2025, 2025
On-Device Dynamic DNN Inference through Spatial Sparsity Exploitation
Published in GetMobile 2025, 2025
TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling
Published in EuroSys 2026, 2026
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Published in MobiSys 2026, 2026
LeanStream: A Speculate-and-Refine Streaming Framework for Efficient On-Device LLM Inference
Published in MobiCom 2026, 2026