114 citations · 156 across the 34 of their papers we have counts for
10 papers · 1 filter
EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
Yize Wu, Ke Gao, Ling Li +1
Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions are typically skewed across e…
Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation
Yize Wu, Ke Gao, Ling Li +1
Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as , where is the ori…
ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
Haolin Pan, Lianghong Huang, Jinyuan Dong +2
Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suf…
Exploring the Feasibility of End-to-End Large Language Model as a Compiler
Hongbin Zhang, Shihao Gao, Yang Liu +3
In recent years, end-to-end Large Language Model (LLM) technology has shown substantial advantages across various domains. As critical system software and infrastructure, compilers…
Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
Haolin Pan, Jinyuan Dong, Hongbin Zhang +3
Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization.…
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
Hongyu Lin, Yuchen Li, Haoran Luo +4
Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains challenging due to the complex kernel space, sparse performance feedback, and strong…
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
Qirui Zhou, Shaohui Peng, Weiqiang Xiong +11
The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely u…
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
Haolin Pan, Hongyu Lin, Haoran Luo +5
Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large L…
QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives
Xuzhi Zhang, Shaohui Peng, Qirui Zhou +12
Computation-intensive tensor operators constitute over 90\% of the computations in Large Language Models (LLMs) and Deep Neural Networks.Automatically and efficiently generating hi…
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
Yize Wu, Ke Gao, Ling Li +1
Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which…