8 papers · 1 filter
D-Quant: Driftable Entropy Coding for KV Cache Quantization
Yi Su, Hong Liu, Guanghua Yu +1
The KV cache has become a major bottleneck in deploying LLMs, as its memory footprint grows linearly with sequence length and batch size, imposing substantial pressure on both memo…
CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
Yufei Xue, Lin Niu, Hong Liu +6
The quadratic cost of self-attention makes long-context inference prohibitively expensive, and proxy-based block-sparse attention has become a practical remedy. Existing methods ty…
AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding
Hong Liu, Rui Cen, Junhan Shi +10
Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best across real-world workloads…
PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention
Hong Liu, Yuan Cheng, Lin Niu +5
Token-level sparse attention, as implemented by DeepSeek Sparse Attention (DSA) in production systems, makes the downstream attention efficient but shifts the bottleneck to the ind…
D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
Tianyu Liu, Yuhao Shen, Rui Cen +7
Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performan…
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
Jiebin Zhang, Zhenghan Yu, Song Liu +9
Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an enti…
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…