Author

Shresth Mishra

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access 2026

PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models

PE-QAT is introduced, a parameter-efficient framework targeting per-channel 4-bit weight-activation quantization of LLMs, which aims to preserve model accuracy while significantly reducing resource requirements and mitigate the impact of severe activation outliers.

Shresth Mishra · Annual Meeting of the Associ... · 0 citations