1 citations · 4 across the 7 of their papers we have counts for
7 papers
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving
Huanqi Hu, Bowen Xiao, Shixuan Sun +8
Quantization is a critical technique for accelerating LLM inference by reducing memory footprint and improving computational efficiency. Among various schemes, 4-bit weight and 8-b…
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
Understanding Parameter Sharing in Transformers
Ye Lin, Mingxuan Wang, Zhexi Zhang +3
Parameter sharing has proven to be a parameter-efficient approach. Previous work on Transformers has focused on sharing parameters in different layers, which can improve the perfor…
MobileNMT: Enabling Translation in 15MB and 30ms
Ye Lin, Xiaohui Wang, Zhexi Zhang +3
Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on d…
PARAGEN : A Parallel Generation Toolkit
Jiangtao Feng, Yi Zhou, Jun Zhang +7
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation. PARAGEN provides thirteen types of customizable plugins, helping users to experiment quickly…
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Xiaoxing Wang, Xiangxiang Chu, Yuda Fan +4
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet re…