14× faster embeddings: how we rebuilt the ONNX path in Manticore
snikolaev
13 points
0 comments
July 03, 2026
Related Discussions
Found 5 related stories in 763.7ms across 14,015 title embeddings via pgvector HNSW
- Executing programs inside transformers with exponentially faster inference u1hcw9nx · 17 pts · March 12, 2026 · 54% similar
- Manticore Search 27.1.5: Auth, sharding, conversational and faster vector search snikolaev · 34 pts · June 22, 2026 · 54% similar
- Making LLM Training Faster with Unsloth and NVIDIA segmenta · 114 pts · May 07, 2026 · 52% similar
- Homomorphically encrypted CIFAR-10 inference in 200ms j2kun · 69 pts · July 17, 2026 · 50% similar
- Real-time LLM Inference on Standard GPUs: 3k tokens/s per request NicoConstant · 202 pts · May 29, 2026 · 49% similar