SubQ: Sub-quadratic LLM built for 12M-token context

Related Discussions

Found 5 related stories in 725.8ms across 14,015 title embeddings via pgvector HNSW

• SubQ: a sub-quadratic LLM with 12M-token context mitchwainer · 46 pts · May 05, 2026 · 95% similar
• The context window has been shattered: Subquadratic debuts a 12M token window gmays · 42 pts · May 09, 2026 · 68% similar
• SubQ – a major breakthrough in LLM intelligence vanni · 20 pts · May 05, 2026 · 64% similar
• Real-time LLM Inference on Standard GPUs: 3k tokens/s per request NicoConstant · 202 pts · May 29, 2026 · 58% similar
• Advanced Quantization Algorithm for LLMs lastdong · 121 pts · May 01, 2026 · 57% similar