Christopher De Sa

Efficiency & Compression · with Chee · 2024

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Christopher De Sa trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Tri Dao

Papers from Christopher De Sa's perspective

Ordered by how strongly the researchers Christopher De Sa trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Llama 2: Open Foundation and Fine-Tuned Chat Models (arXiv.org)
  2. Up or Down? Adaptive Rounding for Post-Training Quantization
  3. QuIP: 2-Bit Quantization of Large Language Models With Guarantees (Neural Information Processing Systems)
  4. The case for 4-bit precision: k-bit Inference Scaling Laws
  5. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
  6. Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions
  7. SqueezeLLM: Dense-and-Sparse Quantization (International Conference on Machine Learning)
  8. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
  9. Vector Quantization
  10. A Simple and Effective Pruning Approach for Large Language Models (International Conference on Learning Representations)

Their papers