Kiln
A WebGPU alternative to transformers.js, 2.2× faster (median)
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
HN · launched Nov 12, 2026 · 5 upvotes (top 86%) · 0 views
Niche: machine learning inference engines · 108 launches, 8 in the last 7 days ▼ -27% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
Visit website ↗ Source listing ↗
More like this: all 108 launches in machine learning inference engines →
Could you build this?
No Kiln is a WebGPU inference runtime claimed to be 2.2× faster than transformers.js. Beating that requires low-level GPU kernel and compiler engineering, which vibe coding cannot reliably deliver.
What it would actually take: A real version needs a WebGPU/WGSL compute backend with hand-tuned kernels for attention, matmul and quantized ops, plus graph-level optimization and memory management in the browser. It requires GPU performance engineering expertise and extensive benchmarking across hardware and browsers.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one : 4518 launches clear the similarity bar, closest 8 shown.
Attention rank: #3731 of 4519 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 379 days after the earliest competitor.
- Small World · hn · 2026-07-05 · 7 upvotes · similarity 0.64
- three-avbd · github · 2026-09-24 · 48 upvotes · similarity 0.64
- GraphGPU · hn · 2026-03-02 · 6 upvotes · similarity 0.63
- runntime · github · 2026-09-14 · 43 upvotes · similarity 0.63
- webgpu-ray-tracing · github · 2026-10-20 · 12 upvotes · similarity 0.62
- steel-webgpu · github · 2026-11-09 · 26 upvotes · similarity 0.62
- casa-ocaso · github · 2026-11-03 · 32 upvotes · similarity 0.61
- rune · github · 2026-10-22 · 78 upvotes · similarity 0.60
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.