Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernelsnanduruganesh.github.io35 points·by rawsh·15 小時前·5 comments
Zyphra ZAYA1-base: First large-scale model trained on AMDzyphra.com6 points·by rawsh·8 個月前·1 comments
Debugging divergence between engine and transformers logprobs for RLgist.github.com2 points·by rawsh·10 個月前·0 comments