Paper Accepted at SC 2026

Tue, 04 Aug 2026 00:00:00 +0000

Our paper LLMPROF: Identifying Performance Bottlenecks in LLM Serving Systems with Top-Down Profiling, by Tianle Zhong, Mao Lin, Hao Wu, Keren Zhou, and Geoffrey Fox, has been accepted at SC 2026, The International Conference for High Performance Computing, Networking, Storage, and Analysis (Supercomputing). Congratulations to all the authors!

Continuous GPU and LLM Profiling Talk @ Scalable Tools Workshop

Tue, 28 Jul 2026 00:00:00 +0000

Keren Zhou presented Very Low-Overhead Continuous Profiling of GPU-Accelerated LLM Workloads at the Scalable Tools Workshop on July 28, 2026. The talk was held from 9:30–10:00 a.m. in Talk Session 5.

The presentation describes the latest progress on Proton toward continuous, production-grade profiling for GPU-accelerated LLM serving and reinforcement-learning workloads with less than 1% overhead. It covers selective and phase-based profiling, memory-efficient metadata handling, lock-free metric collection, and fine-grained visibility into graph-executed GPU workloads.

View the slides

LLM Systems | CAT LAB

Paper Accepted at SC 2026

Continuous GPU and LLM Profiling Talk @ Scalable Tools Workshop