Tag: llm
All the articles with the tag "llm".
-
Trading MatMuls for SRAM Lookups: A 3-Bit Edge Architecture
What if we could run inference with a small set of tensor cores?
-
An approach to calibrating LLM reasoning effort
Controlling reasoning effort in LLMs ( the gpt-oss-style ) and Calibrating LLM Reasoning effort via Label-Free Alignment.
-
Stop Using Embeddings for Everything in RAG
Why deterministic query translation should often come before embeddings in enterprise RAG systems, and how to combine both in a hybrid approach.