[12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS #11

penpaperkeycode · 2022-10-11T11:19:09Z

Date: 2022.12.13
Presenter: Jeonghoon Kim
Keywords: Post-training quantization, GPT, causal language model task, acceleration, cuda kernel

A100 1장으로 175B까지 PTQ하는 논문 입니다.
방법론 자체가 기존 SOTA 방법과는 많이 달라 신기해서 관심을 많기 갖고 있는 논문입니다.

Paper(ICLR2023): https://openreview.net/forum?id=tcbBPnfwxS

penpaperkeycode changed the title ~~[11/29]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS~~ [12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS Oct 11, 2022

penpaperkeycode self-assigned this Oct 25, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS #11

[12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS #11

penpaperkeycode commented Oct 11, 2022 •

edited

Loading

[12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS #11

[12/13]GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS #11

Comments

penpaperkeycode commented Oct 11, 2022 • edited Loading

penpaperkeycode commented Oct 11, 2022 •

edited

Loading