Beidi Chen

beidic's activity

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

authored a paper 24 days ago

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

Paper • 2502.12574 • Published 25 days ago • 11

upvoted a paper 6 months ago

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Paper • 2408.11049 • Published Aug 20, 2024 • 13

authored a paper 10 months ago

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution

Paper • 2405.19325 • Published May 29, 2024 • 14

authored 3 papers 11 months ago

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25, 2024 • 78

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Paper • 2404.11912 • Published Apr 18, 2024 • 17

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12, 2024 • 67

authored a paper about 1 year ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6, 2024 • 186

authored 2 papers over 1 year ago

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Paper • 2310.17157 • Published Oct 26, 2023 • 14

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Paper • 2303.06865 • Published Mar 13, 2023 • 1