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 H100✕

20 operations match

Pick one to compare its implementations; your filters carry over

Operation

Family

Published runs

Last run

Conv gated projection with causal convnone on H100mlp342026-08-24 Decoder layer fused attention MLPnone on H100mlp322026-08-23 Feedforward MLP backwardnone on H100mlp212026-08-18 FFN GELU projection fused backwardnone on H100mlp302026-08-24 Flux feedforward GELU approximatenone on H100mlp312026-08-19 FP8 MLP gate up projectionnone on H100mlp502026-08-23 Fused gate up projection with SwiGLUnone on H100mlp412026-08-24 Fused gated MLP SiLUnone on H100mlp382026-08-24 Fused linear GELU GRN linearnone on H100mlp362026-08-23 Fused residual RMS MLPnone on H100mlp332026-08-15 GeGLU activationnone on H100mlp272026-08-24 GELU approximate feedforward backwardnone on H100mlp192026-08-19 Language model decoder prenorm attention FFN residual backwardnone on H100mlp262026-08-22 LM head projection with logit slicingnone on H100mlp452026-08-13 SiLU activation backwardnone on H100mlp262026-08-24 SwiGLU MLP backwardnone on H100mlp292026-08-24 Text decoder layer with self attention and MLPnone on H100mlp372026-08-23 Video latent GELU activationnone on H100mlp342026-08-15 Vision MLP GELU backwardnone on H100mlp322026-08-24 Vision patch merger spatial shuffle MLPnone on H100mlp292026-08-11

Ranked only against runs that measured the same thing.