🧰 GPTQ

The items that name it 5

• MPQ: A Message-Passing View of Post-Training Quantization
  paperas frameworks and tools2026-10-23

  Existing post-training quantization solver that commits each weight block to a single codeword before neighbors are considered; used as a hard-decision baseline.

• FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
  paperas frameworks and tools2026-10-16

  Weight quantisation method compared with round-to-nearest in the same INT4 format

• DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
  paperas classification.key entities2026-09-25
• The Roadmap to Mastering LLM Inference Optimization
  articleas classification.key entities2026-09-21
• patchy631/time-to-first-token
  repoas classification.key entities2026-08-02