collaborators

7 papers

cs.AI2026

CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits

Xue-Jian Gao, Deng Pan, Yueming Su +12

AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost e…

stat.ML2026

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference

Lingchao Zheng, Yuwei Fan, Jun Li +5

Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplicatio…

stat.ML2026

AIS: Adaptive Importance Sampling for Quantized RL

Jiajun Zhou, Wei Shao, Lingchao Zheng +2

Reinforcement learning (RL) for large language models (LLMs) is dominated by the cost of rollout generation, which has motivated the use of low-precision rollouts (e.g., FP8) paire…

cs.LG2026

Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads

Chendong Song, Meixuan Wang, Hang Zhou +5

Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensiv…

cs.DC2026

Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale

Tianci Bu, Yuan Lyu, Zixi Chen +6

Data-parallel (DP) load balancing has emerged as a first-order bottleneck in large-scale LLM serving. When a model is sharded across devices via tensor parallelism (TP) or expert p…

cs.CL2025

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model

Wei Shao, Lingchao Zheng, Pengyu Wang +3

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimi…