Zhihao Jia
where else to find them
no profile links on file
what they talk about
all 6 in the filters
where they keep going back
no series more than once — all 7 in the filters
on a stage with
all 59 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees | NSDI '26 | 2026-05-04 |
FlexLLM co-serves LLM inference and PEFT finetuning on the same GPUs by fusing inference and adapter forward passes and splitting backward work across steps… | ||
| Mirage: A Multi-Level Superoptimizer for Tensor Programs | OSDI '25 | 2025-07-07 |
Mirage is a multi-level superoptimizer that generates custom CUDA kernels from tensor programs using a uniform representation across kernel, thread-block, and… | ||
| Quarl: A Learning-Based Quantum Circuit Optimizer | OOPSLA 2024 | 2024-10-20 |
Quarl is a reinforcement-learning quantum circuit optimizer that replaces greedy search with a policy trained via PPO, decomposes millions of actions into a… | ||
| Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
Parcae is a system that proactively adapts hybrid data+pipeline parallelization to predicted spot-instance changes, using a liveput metric that balances… | ||
| EINNET: Optimizing Tensor Programs with Derivation-Based Transformations | OSDI 2023 | 2023-07-10 |
EinNet claims a larger optimizer search space by turning tensor programs into tensor expressions and applying derivation-based tensor expression… | ||
| Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs | NSDI 2023 | 2023-04-17 |
Bamboo makes preemptible (spot) instances usable for large DNN training by building a distributed system that inserts redundant computations into idle pipeline… | ||
| TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed... | NSDI 2023 | 2023-04-17 |
TopoOpt co-optimizes computation, communication, and physical network topology to speed distributed DNN training, claiming up to 3.4x faster 99th-percentile… | ||
| PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated | 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI '21) | 2021-07-14 |
PET applies partially equivalent transformations plus automated corrections to expand the tensor-program search space and finds faster kernels by combining… | ||
| Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and | 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI '21) | 2021-07-14 |
Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads
John Thorpe, Yifan Qiao, Jonathan Eyolfson, and… | ||
| nothing matches | ||