#autoregressive decoding
Autoregressive Decoding: 2 AI articles covering autoregressive decoding news, analysis, and research
Articles
AutoIndexer: Flexible-Order Decoding by Training Causal ModelsNEW⭐8
AutoIndexer trains causal models on chains of edits, enabling flexible-order decoding with token insertions, substitutions, and deletions for post-hoc context e...
Accelerating LLM Inference via Vector Index Based Output Embeddings⭐10
Vector index-based output embeddings accelerate LLM decoding by replacing dense projections with HNSW retrieval, boosting throughput up to 82% while preserving ...