6 papers
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao +30
Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose lo…
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
Xun Sun, Shaoyuan Chen, Pingchuan Ma +18
Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instance. This efficiency c…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
Yongtong Wu, Shaoyuan Chen, Yinmin Zhong +10
The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading th…
OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs
Shaoyuan Chen, Zhixuan Chen, Dawei Yang +2
Large Language Models (LLMs) fine-tuning techniques not only improve the adaptability to diverse downstream tasks, but also mitigate adverse effects of model quantization. Despite…
Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation
Shaoyuan Chen, Wencong Xiao, Yutong Lin +5
Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient…