LeapQuant quantizes linear attention states to 8/4-bit training-free with 2x throughput
zealcaiden · x · 2026-11-13
LeapQuant targets the next bottleneck in Linear Attention models: the recurrent state itself. It compresses linear states to 8/4-bit in a training-free way with no accuracy degradation, while improving throughput by 2x — a direct engineering win for deploying linear attention architectures.
Related event: LeapQuant: Training-Free Quantization Speeds Up Linear Attention(4 posts)→
More from Infra
- DeepSeek V4.1-Flash seeds resist 4.3B-seed search; Huawei chip shift rumored — TheNormanMu · 2026-11-13
- OpenCartridge's trust bill: no auth, public bucket, Docker socket exposed — maier_ak · 2026-11-13
- camenduru open-sources OpenCartridge, packaging AI models as one-click 'cartridges' — maier_ak · 2026-11-13
- Game assets on your own GPU: what OpenCartridge does and what it asks you to trust — maier_ak · 2026-11-13
- Core Memory podcast: Sceye's $100M high-altitude airship wins SoftBank fleet order for Japan broadband — kyliebytes · 2026-11-13
- Torus explains closed-loop liquid cooling: no on-site water hookup needed — ccerrato147 · 2026-11-13