Beidi Chen
20 papers · 3184 citations
Most-cited papers
- Efficient Streaming Language Models With Attention Sinks2023 · 1654 citations
- Deja Vu: Contextual Sparsity For Efficient Llms At Inference Time2023 · 317 citations
- Layerskip: Enabling Early Exit Inference And Self-speculative Decoding2024 · 234 citations
- Triforce: Lossless Acceleration Of Long Sequence Generation With Hierarchical Speculative Decoding2024 · 97 citations
Topics