7 papers
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…
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…
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…
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…
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…
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…