# usagi

- **Event:** [PyTorch Helion Hackathon](https://cerebralvalley.ai/e/helion-hackathon)
- **When:** Sat, Mar 14 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Sissi Wang](https://cerebralvalley.ai/u/sissississi_013)
- **GitHub:** https://github.com/pytorch/helion/pull/1713, https://github.com/pytorch/helion/pull/1714, https://github.com/pytorch/helion/pull/1715, https://github.com/pytorch/helion/pull/1716
- **Gallery:** https://cerebralvalley.ai/e/helion-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/helion-hackathon/hackathon/gallery/13

implemented all 4 scored Helion kernels for Gated DeltaNet and causal conv1d, optimized for B200 GPUs with per-shape autotuned configs.

causal_conv1d: Zero-copy causal depthwise conv: eliminated external padding via in-kernel index clamping/masking, avoiding redundant memory traffic from torch.cat. ~2.9x speedup over naive padded approach. TMA + 6-stage pipelining, hl.specialize(W) for compile-time unrolling.

gated_deltanet_chunk_fwd_h: Inter-chunk state recurrence with sequential scan, maintaining [K,V] hidden state in registers. hl.dot with accumulator for state updates, multi-stage pipelining, tuned loop orders, variable static_ranges handling.

gated_deltanet_recompute_w_u: WY-transform kernel computing w and u as two fused dot products sharing a single A matrix load. Mixed tensor_descriptor/pointer indexing, hl.specialize for K, V, and chunk dims.

gated_deltanet_chunk_fwd_o: Output kernel combining inter-chunk (q@h) and intra-chunk (causal attention). Early inter-chunk computation for better pipelining, causal masking via hl.arange, persistent_interleaved pid with num_sm_multiplier=8 for full SM utilization.

---

Markdown version of https://cerebralvalley.ai/e/helion-hackathon/hackathon/gallery/13. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt