Skip to content

Search Models Records GPUs Docs

More

Records GPUs Docs

Kernels Serving

⏎

Feed Serving Projects Challenges Contribute Sources Methodology Legal GitHub Atom llms.txta46b010

Kernels Serving

⏎

gpu B200✕

12 operations match

Pick one to compare its implementations; your filters carry over

Operation

Family

Published runs

Last run

Flux multi head RMSNorm QK29 on B200 · best 23.0 µsrmsnorm292026-08-23 Fused add RMSNorm h2048131 on B200 · best 4.33 µs · 56 with sourcermsnorm1312026-08-24 Fused add RMSNorm h7168112 on B200 · best 7.16 µs · 56 with sourcermsnorm1122026-08-15 RMSNorm h128184 on B200 · best 3.64 µs · 126 with sourcermsnorm1842026-08-19 RMSNorm h51293 on B200 · best 2.73 µs · 56 with sourcermsnorm932026-08-21 RMSNorm h153699 on B200 · best 3.33 µs · 64 with sourcermsnorm992026-08-21 RMSNorm h4096131 on B200 · best 5.75 µs · 84 with sourcermsnorm1312026-08-21 RMSNorm h7168103 on B200 · best 6.15 µs · 56 with sourcermsnorm1032026-08-21 Fused add RMSNorm h5376none on B200rmsnormnone yet—RMSNorm h3072none on B200rmsnormnone yet—RMSNorm h5120none on B200rmsnormnone yet—RMSNorm h5376none on B200rmsnormnone yet—

Ranked only against runs that measured the same thing.