News for hackers. Stuff that matters.
Re:Show HN: Sparse Matrix-Vector Multiplication that works a... by jjgreen on Tuesday November 25, 2025 @09:58AM (#46046325)
Interesting approach -- thanks
Re:Show HN: Sparse Matrix-Vector Multiplication that works a... by fleahunter on Tuesday November 25, 2025 @07:16PM (#46052551)
Interesting approach! I've been thinking a lot about how often we get caught up in striving for extreme sparsity without considering the practical implications of using pruned models on consumer hardware. It reminds me of a project I worked on where we had to optimize for both performance and memory constraints, and we found ourselves tangled in the weeds of matrix representation.

I'm curious about your performance metrics—did you find any surprising edge cases when dealing with certain sparsity patterns on different GPUs? I can imagine folks running LLMs on consumer devices will appreciate any optimizations that help squeeze out more efficiency, especially if they’re dealing with larger models. And you mentioned that the MACKO format works across all GPUs—this could really democratize these technologies. That's exciting!

Have you thought about how this might impact other areas of machine learning or even classical algorithm work? I'd love to hear more about the community's thoughts on bridging the gap between pruning and quantization too.

Re:Show HN: Sparse Matrix-Vector Multiplication that works a... by vlejd on Wednesday November 26, 2025 @01:30PM (#46060778)
Interestingly enough, we found that cublas is not that well optimized for some less common consumer GPUs, specifically 3090. We saw that is didn't really achieve it's full potential for a lot of different matrix shapes, probably because of poor tuning. Interestingly enough, out kernel does not have any parameters, and it was able to outperform cublas even in setting where it has no right to do so.

Regarding patterns, we tested mainly random matrices and ones created by Wanda pruning. 2:4 sparsity (commonly used structure) will have same results as random matrix (probably even better). Interestingly enough, block sparsity could have very close to a worst case scenario with our format, because it promotes disproportional long sequences of zeroes.

Regarding other usecases, we are looking into it, but most common ones we found are usually for much smaller sparsity <1%. If you know about some other use case that is in the 30-90 range, let us know.

Re:Show HN: Sparse Matrix-Vector Multiplication that works a... by jjgreen on Thursday November 27, 2025 @07:46AM (#46068758)