Pinned Repositories
COMP4901Y_Course_HKUST
Course Material for the UG Course COMP4901Y
Cross_Region_VPN_Profiling
FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
HexGen
[ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
Relaxed System Lab's Repositories
Relaxed-System-Lab/COMP4901Y_Course_HKUST
Course Material for the UG Course COMP4901Y
Relaxed-System-Lab/HexGen
[ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
Relaxed-System-Lab/Cross_Region_VPN_Profiling
Relaxed-System-Lab/FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.