Pengle Zhang

Chaojun Xiao, Yuqi Luo, Wenbin Zhang et al. · tencent-ai

Pre-trained language models (PLMs) have achieved remarkable results on NLP tasks but at the expense of huge parameter sizes and the consequent computational costs. In this paper, we propose Variator, a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins. Compression plugins are designed to reduce the sequence length via compressing multiple hidden vectors into one and trained with original PLMs frozen. Different from traditional model acceleration methods, which compress PLMs to smaller sizes, Variator offers two distinct advantages: (1) In real-world applications, the plug-and-play nature of our compression plugins enables dynamic selection of different compression plugins with varying acceleration ratios based on the current workload. (2) The compression plugin comprises a few compact neural network layers with minimal parameters, significantly saving storage and memory overhead, particularly in scenarios with a growing number of tasks. We validate the effectiveness of Variator on seven datasets. Experimental results show that Variator can save 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%. Moreover, when the model scales to billions of parameters, Variator matches the strong performance of uncompressed PLMs.

Chaojun Xiao, Pengle Zhang, Xu Han et al. · tencent-ai

Large language models (LLMs) have emerged as a cornerstone in real-world applications with lengthy streaming inputs (e.g., LLM-driven agents). However, existing LLMs, pre-trained on sequences with a restricted maximum length, cannot process longer sequences due to the out-of-domain and distraction issues. Common solutions often involve continual pre-training on longer sequences, which will introduce expensive computational overhead and uncontrollable change in model capabilities. In this paper, we unveil the intrinsic capacity of LLMs for understanding extremely long sequences without any fine-tuning. To this end, we introduce a training-free memory-based method, InfLLM. Specifically, InfLLM stores distant contexts into additional memory units and employs an efficient mechanism to lookup token-relevant units for attention computation. Thereby, InfLLM allows LLMs to efficiently process long sequences with a limited context window and well capture long-distance dependencies. Without any training, InfLLM enables LLMs that are pre-trained on sequences consisting of a few thousand tokens to achieve comparable performance with competitive baselines that continually train these LLMs on long sequences. Even when the sequence length is scaled to $1,024$K, InfLLM still effectively captures long-distance dependencies. Our code can be found in \url{https://github.com/thunlp/InfLLM}.

Yuxiang Chen, Xiaoming Xu, Pengle Zhang et al.

Large Language Models (LLMs) training is prohibitively expensive, driving interest in low-precision fully-quantized training (FQT). While novel 4-bit formats like NVFP4 offer substantial efficiency gains, achieving near-lossless training at such low precision remains challenging. We introduce TetraJet-v2, an end-to-end 4-bit FQT method that leverages NVFP4 for activations, weights, and gradients in all linear layers. We identify two critical issues hindering low-precision LLM training: weight oscillation and outliers. To address these, we propose: 1) an unbiased double-block quantization method for NVFP4 linear layers, 2) OsciReset, an algorithm to suppress weight oscillation, and 3) OutControl, an algorithm to retain outlier accuracy. TetraJet-v2 consistently outperforms prior FP4 training methods on pre-training LLMs across varying model sizes up to 370M and data sizes up to 200B tokens, reducing the performance gap to full-precision training by an average of 51.3%.

Jintao Zhang, Haofeng Huang, Pengle Zhang et al. · tsinghua

Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2, which utilizes significantly faster 4-bit matrix multiplication (Matmul) alongside additional precision-enhancing techniques. First, we propose to quantize matrices $(Q, K)$ to INT4 in a hardware-friendly thread-level granularity and quantize matrices $(\widetilde P, V)$ to FP8. Second, we propose a method to smooth $Q$, enhancing the accuracy of INT4 $QK^\top$. Third, we propose a two-level accumulation strategy for $\widetilde PV$ to enhance the accuracy of FP8 $\widetilde PV$. The operations per second (OPS) of SageAttention2 surpass FlashAttention2 and xformers by about 3x and 4.5x on RTX4090, respectively. Moreover, SageAttention2 matches the speed of FlashAttention3(fp8) on the Hopper GPUs, while delivering much higher accuracy. Comprehensive experiments confirm that our approach incurs negligible end-to-end metrics loss across diverse models, including those for language, image, and video generation. The code is available at https://github.com/thu-ml/SageAttention.

Jintao Zhang, Xiaoming Xu, Jia Wei et al. · tsinghua

The efficiency of attention is critical because its time complexity grows quadratically with sequence length. SageAttention2 addresses this by utilizing quantization to accelerate matrix multiplications (Matmul) in attention. To further accelerate SageAttention2, we propose to utilize the faster instruction of FP8 Matmul accumulated in FP16. The instruction is 2x faster than the FP8 Matmul used in SageAttention2. Our experiments show that SageAttention2++ achieves a 3.9x speedup over FlashAttention while maintaining the same attention accuracy as SageAttention2. This means SageAttention2++ effectively accelerates various models, including those for language, image, and video generation, with negligible end-to-end metrics loss. The code will be available at https://github.com/thu-ml/SageAttention.

Pengle Zhang, Jia Wei, Jintao Zhang et al. · tsinghua

Transformer models have achieved remarkable success across various AI applications but face significant training costs. Low-bit training, such as INT8 training, can leverage computational units with higher throughput, and has already demonstrated its effectiveness on GPT2 models with block-level quantization. However, it struggles with modern Transformer variants incorporating GLU units. This is because those variants demonstrate complex distributions of activation outliers. To address the challenge, we propose Fallback Quantization, implementing mixed-precision GEMM that dynamically falls back 8-bit to 16-bit for activation blocks containing outliers. Experiments show that our approach is robustly competent in both fine-tuning and pretraining settings. Moreover, our method achieves a 1.57x end-to-end training speedup on RTX4090 GPUs.

Weiyu Huang, Pengle Zhang, Xiaolu Zhang et al.

Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplicative gate for each component under an l0 sparsity constraint. Due to the discreteness of the l0 norm, prior work typically adopts stochastic hard-concrete relaxations to enable differentiable optimization; however, this stochasticity can introduce a train--test mismatch when sampled masks are discretized for deployment and restricts masks to a bounded, near-binary range. To address this, we propose Deterministic Differentiable Pruning (DDP), a mask-only optimization method that eliminates stochasticity by directly optimizing a deterministic soft surrogate of the discrete l0 objective. Compared with prior approaches, DDP offers greater expressiveness, reduced train--test mismatch, and faster convergence. We apply our method to several dense and MoE models, including Qwen3-32B and Qwen3-30B-A3B, achieving a performance loss as small as 1% on downstream tasks while outperforming previous methods at 20% sparsity. We further demonstrate end-to-end inference speedups in realistic deployment settings with vLLM.