Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernelsnanduruganesh.github.io21 points·by rawsh·5시간 전·0 comments
Zyphra ZAYA1-base: First large-scale model trained on AMDzyphra.com6 points·by rawsh·8개월 전·1 comments
Debugging divergence between engine and transformers logprobs for RLgist.github.com2 points·by rawsh·10개월 전·0 comments