qr-decomposition

Tag

Cards List
#qr-decomposition

@PyTorch: @marksaroufim Fewer training steps don’t necessarily mean faster training. At #PyTorchCon 2026 (@coreauto) examines the…

X AI KOLs Following ↗ · 2026-10-21 Cached

在 PyTorch Con 2026 上,Mark Saroufim 探讨了支撑更优优化器的线性代数内核,涵盖 QR、对称特征分解与 Cholesky,并从 GPU MODE 的线性代数竞赛中总结了如何通过暴露并行性、重叠独立阶段和合并更新来减少数据搬运。

0 favorites 0 likes
#qr-decomposition

Auto-research with codex: How I achieved a 232x Faster Kernel

Hacker News Top ↗ · 2026-08-15 Cached

A blog post detailing how the author used Codex to optimize a kernel in a GPU Mode contest, achieving a 232x speedup in QR decomposition and sharing learnings on auto-research.

0 favorites 0 likes
#qr-decomposition

@dejavucoder: my latest blog post "auto-research with codex: how I achieved a 212x faster kernel over baseline with codex in GPU Mode…

X AI KOLs Timeline ↗ · 2026-07-08 Cached

Blog post by Sankalp detailing how he used Codex to achieve a 232x faster GPU kernel for QR decomposition in GPU Mode's contest, outlining his auto-research methodology.

0 favorites 0 likes
#qr-decomposition

Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage

arXiv cs.LG ↗ · 2026-05-27 Cached

This paper proposes a reparametrization of the preconditioner in Shampoo-based optimization methods (like KL-Shampoo and SOAP) to support BFloat16 storage and reduce computational overhead by updating only part of the basis via QR decomposition in a subspace, making these methods more memory- and time-efficient.

0 favorites 0 likes
← Back to home

Submit Feedback