Omri Weinstein
@WeinsteinOmri
Computer scientist, co-founder of @prlnet, ex-Nvidia, Vast Data, Princeton PhD, ¶
209 Following 3.3K Followers
Pearl (@prlnet) has the fastest FP8 MoE Kernels for Blackwell chips!
Group-Matrix-Multiplication is one of the most optimized operations in AI. As a former researcher at @nvidia I can say firsthand that pushing the performance frontier of MatMuls is... Hard.
Pearl-GEMM is ~5% faster than prior state-of-art Quack (@tri_dao) and ~42% faster than Flashinfer on B200s.
Show more
