Yongkun Li
3 indexed papers
Recent (6 mo)
3With code
0Influential cites
0Benchmarked
0Publications per year
326
Top categories
OS×2Distributed×1
Frequent co-authors
Research Timeline
2026
LUMEN: Coordinated Failure Recovery for Distributed LLM Serving
This paper presents LUMEN, a fault-tolerant LLM serving system that improves serving and recovery times by treating recovery as a load-aware coordination problem.
gKSM: GPU Memory Deduplication at Driver Layer for Serverless LLM Inference
gKSM is a transparent GPU memory deduplication framework for serverless LLM inference that reduces GPU memory usage and improves throughput.
Visual Cache Reuse for Efficient Multimodal Inference
VisMemo is a serving system that enables approximate KV cache reuse for modern vision-language models to reduce prefill latency and memory overhead.
Highlighted terms show continued research focus across papers
Papers
cs.OSEmpiricalRecentOct 18, 2026
gKSM: GPU Memory Deduplication at Driver Layer for Serverless LLM Inference
Shuheng Gao, Fan Guo, Yongkun Li, Ziye Yue +2 more
gKSM is a transparent GPU memory deduplication framework for serverless LLM inference that reduces GPU memory usage and improves throughput.
View →
cs.OSEmpiricalRecent