2 papers
cs.DC2026
VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference
Yan Shi, Xiaochao Wang, Jingchun Gao +7
Chunked prefill pipeline parallelism (CPP) is a key technique for LLM inference. However, equal-size chunks exhibit imbalanced latency, as later chunks attend longer prefix KV cach…
cs.AI2026
Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization
Dongjie Chen, Ping Zhao, Bohua Zhan +11
Recent advances in large language models (LLMs) have enabled automated kernel generation and optimization, but most existing approaches rely on surface signals such as compilation…