1st Place
Axiom
We implemented 4 GPU kernels using Helion DSL targeting NVIDIA B200 (Blackwell) GPUs: 1.
dev toolsscience
Yahya Alhinai
Cerebral Valley · Meta · 2026-03-14 to 2026-03-15
PyTorch Helion Hackathon
Public gallery: every submissionEvent page ↗
- Projects
- 19
- Winners
- 5
- With repo
- 89%
Winners
2nd Place
WarpDrive
Here's how each kernel works: 1.
dev toolsscience
Warren Low, Vishal Goklani, S G +1
3rd Place
Shiprail
using helion with NVIDIA ComputeIQ and TileIR.
dev tools
Brandon In
Finalist
Cappucino
Created a LLM-based-search for autotuner.
dev tools
Salvador Escobedo, Karthik Raja Anandan, Nihal Nihalani +13
Finalist
cob-farmers
fully autokernel generated
dev toolsscience
Fabrizio Milo
All other submissions
14Buba Shrimp
Optimized code for each kernel is listed under respective folder
dev toolsscience
Raka Kumar
LilyErnest
Autotuned kernels
dev tools
Lily Su, Ernest Yeung
RAP
f
dev tools
Ronit Mathur
vectorblock.io
causal_conv1d - brief summary reading, it's functionality not known and performance not known fp8_quant_py - brief summary reading, it's functionality not known and performance not known gated_deltanet_chunk_fwd_h_py - b
dev toolsscience
Suvasis Mukherjee
Clio AI
gated_deltanet_recompute_w_u/submission/submission.py in the repo computes the Gated DeltaNet WY-transform forward outputs (w, u) from raw inputs (k, v, beta, A, g).
dev tools
Ankit Maloo
Team Manifold - includes NVIDIA employee
We removed all the extra compute in all the kernels.
dev tools
Josh Rauvola, Andrew Briand
KernIt_Raj
Leaderboard name: bloomberg9383 All 5 kernels implemented in Helion DSL for Gated DeltaNet on B200: 1.
dev tools
Raj Kolamuri
RackSavant AI
Problem 3 (gated_deltanet_chunk_fwd_h): Implemented inter-chunk state recurrence kernel for Gated DeltaNet using Helion DSL with hardcoded configs optimized for B200.
dev tools
RackSavant AI
Team Beaker (CodingMaster)
N/A
dev tools
Jaden Rodriguez
Noob
I autotuned the kernels and tried to do some DMA-Compute overlapping, though that wasn't really effective.
dev tools
Jayanth Sadhasivan
heisenberg
https://github.com/narain1/helion-hack/blob/main/submission_fp8_quant.py
dev tools
narain p
DPI Research
Not sure where the f8_quant submission is supposed to go, so here it is: https://github.com/dpiresearch/Helion_20260314/blob/main/helion/fp8_quant_py/submission.py For causal_conf1d Tuned the Helion execution config so t
dev toolsscience
Daniel Pang
Pradeep
4 kernels submitted with optimizations
dev tools
Pradeep Banavara, Aaron Fanous
Battlestars
We implemented four kernels for the Helion challenge on NVIDIA B200 GPUs, prioritizing FP32 accumulation for precision and 3D tiling for better hardware occupancy.
dev toolsscience
Jorge Jimenez, Gretchen Boria