wang

wangxbx's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 1 day ago

Qwen/QwQ-32B

Text Generation • Updated about 9 hours ago • 44.8k • • 1.37k

upvoted 6 papers 2 days ago

DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting

Paper • 2503.00784 • Published 5 days ago • 9

Speculative Ad-hoc Querying

Paper • 2503.00714 • Published 5 days ago • 12

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Paper • 2503.01743 • Published 4 days ago • 60

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

Paper • 2502.14856 • Published 15 days ago • 7

Iterative Value Function Optimization for Guided Decoding

Paper • 2503.02368 • Published 3 days ago • 14

PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization

Paper • 2503.01328 • Published 4 days ago • 14

liked a Space 4 days ago

Running

2.1k

2.1k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

upvoted 2 papers 6 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published 10 days ago • 51

Rank1: Test-Time Compute for Reranking in Information Retrieval

Paper • 2502.18418 • Published 10 days ago • 25

upvoted 2 papers 10 days ago

MoBA: Mixture of Block Attention for Long-Context LLMs

Paper • 2502.13189 • Published 17 days ago • 13

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published 14 days ago • 26

upvoted 2 papers 13 days ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published 15 days ago • 12

S*: Test Time Scaling for Code Generation

Paper • 2502.14382 • Published 15 days ago • 59

upvoted 6 papers 15 days ago

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Paper • 2502.13965 • Published 16 days ago • 18

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 16 days ago • 156

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

Paper • 2502.12574 • Published 17 days ago • 11

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published 22 days ago • 142

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published 19 days ago • 139

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published 24 days ago • 46