2 citations · 5 across the 6 of their papers we have counts for
6 papers
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…
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Xin Cheng, Rui Tian, Wangding Zeng +18
While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrie…
PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR
Zixuan Ma, Haojie Wang, Jingze Xing +7
Deep neural networks (DNNs) are of critical use in different domains. To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-sp…
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
Kezhao Huang, Haitian Jiang, Minjie Wang +7
A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU. Due to limited GPU memory, expensive d…
OLLIE: Derivation-based Tensor Program Optimizer
Liyan Zheng, Haojie Wang, Jidong Zhai +7
Boosting the runtime performance of deep neural networks (DNNs) is critical due to their wide adoption in real-world tasks. Existing approaches to optimizing the tensor algebra exp…
Comprehensive Framework of RDMA-enabled Concurrency Control Protocols
Chao Wang, Kezhao Huang, Xuehai Qian
In this paper, we develop RCC, the first unified and comprehensive RDMA-enabled distributed transaction processing framework supporting six serializable concurrency control protoco…