search

Deelvin / mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
https://mlc.ai/mlc-llm
Apache License 2.0
0 stars 0 forks source link

Study SOTA of LLM compression #4

Open vvchernov opened 8 months ago

vvchernov commented 8 months ago

Study SOTA approaches and modern papers:

  1. SmoothQuant github
  2. AWQ github
  3. GPTQ
  4. Outlier suppression
  5. Perplexity on WikiText (need find more relevant reference)
  6. HELM (Holistic Evaluation of Language Models)
  7. Outlier suppression+
  8. SpQR
  9. AQAS and SLAC
vvchernov commented 7 months ago

See also resume of some papers here