Re:Show HN: Sparse Matrix-Vector Multiplication that works a...
by vlejd on Tuesday November 25, 2025 @05:45PM
(#46051771)
I think the lack of efficient GPU kernels was the main problem. It is much, much easier to get a real speedup and memory reduction from quantization from fp16 to fp8 than from 50% sparsity. For sparsity you needed structure (which makes your model worse) and special hardware support.
[ Parent
| on HN ]
There are no comments on this comment yet.