한국어EN
Inference Infrastructure & ServingMIT Han Lab (Ji Lin et al.)MIT

AWQ

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

AWQ

Why it matters

Quantization that protects only the top weights as judged by activations; TinyChat runs more than 3× faster than HF FP16

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/2306.00978

Added in Week 35, 2026 · See that week

On the map — ⑧ Inference Infrastructure line

  1. Previous stopSpeculative Decoding
  2. This recordAWQ
  3. Next stopvLLM + PagedAttention
See it on the map

Same week

RefinedWebPaperDPOPaper

Nearby on the same axis

UC Berkeley releases vLLM + PagedAttentionOfficialllama.cpp community introduces the GGUF formatPressGeorgi Gerganov creates the llama.cpp repositoryOfficialAccelerating LLM Decoding with Speculative SamplingPaper