arXiv subjects

Kezhao Huang

Publications and source records attributed to Kezhao Huang.

7 recordsLinked to original sources

arXiv2026

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce conditional memory as a complementary sparsity axis, instantiated via Engram, a module that modernizes classic $N$-gram embedding for O(1) lookup. By formulating the Sparsity Allocation problem, we uncover a U-shaped scaling law that optimizes the trade-off between neural computation (MoE) and static memory (Engram). Guided by this law, we scale Engram to 27B parameters, achieving superior performance over a strictly iso-parameter and iso-FLOPs MoE baseline. Most notably, while the memory module is expected to aid knowledge retrieval (e.g., MMLU +3.4; CMMLU +4.0), we observe even larger gains in general reasoning (e.g., BBH +5.0; ARC-Challenge +3.7) and code/math domains~(HumanEval +3.0; MATH +2.4). Mechanistic analyses reveal that Engram relieves the backbone's early layers from static reconstruction, effectively deepening the network for complex reasoning. Furthermore, by delegating local dependencies to lookups, it frees up attention capacity for global context, substantially boosting long-context retrieval (e.g., Multi-Query NIAH: 84.2 to 97.0). Finally, Engram establishes infrastructure-aware efficiency: its deterministic addressing enables runtime prefetching from host memory, incurring negligible overhead. We envision conditional memory as an indispensable modeling primitive for next-generation sparse models.

cs.CL↗

arXiv2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

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 DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

cs.CL↗

arXiv2025

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2) Scalable Reinforcement Learning Framework: By implementing a robust reinforcement learning protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro, achieving gold-medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). (3) Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This methodology facilitates scalable agentic post-training, yielding substantial improvements in generalization and instruction-following robustness within complex, interactive environments.

cs.CL↗

arXiv2024

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training

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 data movement is necessary to facilitate the storage of these features on alternative devices with slower access (e.g. CPU memory). Moreover, the irregularity of graph structures contributes to poor data locality which further exacerbates the problem. Consequently, existing frameworks capable of efficiently training large GNN models usually incur a significant accuracy degradation because of the currently-available shortcuts involved. To address these limitations, we instead propose FreshGNN, a general-purpose GNN mini-batch training framework that leverages a historical cache for storing and reusing GNN node embeddings instead of re-computing them through fetching raw features at every iteration. Critical to its success, the corresponding cache policy is designed, using a combination of gradient-based and staleness criteria, to selectively screen those embeddings which are relatively stable and can be cached, from those that need to be re-computed to reduce estimation errors and subsequent downstream accuracy loss. When paired with complementary system enhancements to support this selective historical cache, FreshGNN is able to accelerate the training speed on large graph datasets such as ogbn-papers100M and MAG240M by 3.4x up to 20.5x and reduce the memory access by 59%, with less than 1% influence on test accuracy.

cs.LG↗

arXiv2023

PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR

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-specific accelerators. Existing tensor compilers mainly focus on optimizing computation efficiency. However, memory access is becoming a key performance bottleneck because the computational performance of accelerators is increasing much faster than memory performance. The lack of direct description of memory access and data dependence in current tensor compilers' intermediate representation (IR) brings significant challenges to generate memory-efficient code. In this paper, we propose IntelliGen, a tensor compiler that can generate high-performance code for memory-intensive operators by considering both computation and data movement optimizations. IntelliGen represent a DNN program using GIR, which includes primitives indicating its computation, data movement, and parallel strategies. This information will be further composed as an instruction-level dataflow graph to perform holistic optimizations by searching different memory access patterns and computation operations, and generating memory-efficient code on different hardware. We evaluate IntelliGen on NVIDIA GPU, AMD GPU, and Cambricon MLU, showing speedup up to 1.97x, 2.93x, and 16.91x(1.28x, 1.23x, and 2.31x on average), respectively, compared to current most performant frameworks.

cs.LG↗

arXiv2022

OLLIE: Derivation-based Tensor Program Optimizer

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 expression of a DNN only consider expressions representable by a fixed set of predefined operators, missing possible optimization opportunities between general expressions. We propose OLLIE, the first derivation-based tensor program optimizer. OLLIE optimizes tensor programs by leveraging transformations between general tensor algebra expressions, enabling a significantly larger expression search space that includes those supported by prior work as special cases. OLLIE uses a hybrid derivation-based optimizer that effectively combines explorative and guided derivations to quickly discover highly optimized expressions. Evaluation on seven DNNs shows that OLLIE can outperform existing optimizers by up to 2.73$\times$ (1.46$\times$ on average) on an A100 GPU and up to 2.68$\times$ (1.51$\times$) on a V100 GPU, respectively.

cs.LG↗

arXiv2021

Comprehensive Framework of RDMA-enabled Concurrency Control Protocols

In this paper, we develop RCC, the first unified and comprehensive RDMA-enabled distributed transaction processing framework supporting six serializable concurrency control protocols: not only the classical protocols NOWAIT, WAITDIE, and OCC, but also more advanced MVCC and SUNDIAL, and even CALVIN, the deterministic concurrency control protocol. Our goal is to unbiasedly compare the protocols in a common execution environment with the concurrency control protocol being the only changeable component. We focus on the correct and efficient implementation using key techniques, such as co-routines, outstanding requests, and doorbell batching, with two-sided and one-sided communication primitives. Based on RCC, we get the deep insights that cannot be obtained by any existing systems. Most importantly, we obtain the execution stage latency breakdowns with one-sided and two-sided primitive for each protocol, which are analyzed to develop more efficient hybrid implementations. Our results show that three hybrid designs are indeed better than both one-sided and two-sided implementations by up to 17.8%. We believe that RCC is a significant advance over the state-of-the-art; it can both provide performance insights and be used as the common infrastructure for fast prototyping new implementations.

cs.DC↗