Tag: llm

All the articles with the tag "llm".

• Trading MatMuls for SRAM Lookups: A 3-Bit Edge Architecture

  16 Apr, 2026

  By trading heavy FP16 MatMuls for SRAM lookups and 1-bit additions, our custom quantization pipeline squeezes state-of-the-art models down to approx. 3 bits per weight with minimal accuracy loss. Here is how bypassing Tensor Cores could reshape the design of future edge AI chips.

• An approach to calibrating LLM reasoning effort

  17 Feb, 2026

  In this blog post, we will discuss about 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

  11 Dec, 2025

  Why deterministic query translation should often come before embeddings in enterprise RAG systems, and how to combine both in a hybrid approach.