HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rawsh

39 karmajoined hace 6 años

Submissions

Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels

nanduruganesh.github.io
16 points·by rawsh·hace 4 horas·0 comments

Zyphra ZAYA1-base: First large-scale model trained on AMD

zyphra.com
6 points·by rawsh·hace 8 meses·1 comments

Debugging divergence between engine and transformers logprobs for RL

gist.github.com
2 points·by rawsh·hace 10 meses·0 comments