Buba Shrimp

PyTorch Helion Hackathon

Optimized code for each kernel is listed under respective folder

Team

Placement

Participant

More from PyTorch Helion Hackathon

Axiom

We implemented 4 GPU kernels using Helion DSL targeting NVIDIA B200 (Blackwell) GPUs: 1. causal_conv1d: Depthwise causal 1D convolution (core Mamba/Mamba-2…

WarpDrive

Here's how each kernel works: 1. FP8 Quantization (fp8_quant) Memory-bound, fully parallel. Takes float32 activations, groups them (64-128…

Shiprail

using helion with NVIDIA ComputeIQ and TileIR.

cob-farmers

fully autokernel generated

Team SEWR

causal_conv1d: Causal depthwise 1D convolution with static per-shape configs and a stable fused convolution path; this is the highest-confidence officially…

GPU modders