Skip to content

[Quantization] Channel-wise Output Activation Quantization for Attention QKV Modules + KV-cache channel quantization#1233

Draft
horheynm wants to merge 9 commits intomainfrom attn_quant

Commits

Commits on Feb 10, 2025

Commits on Feb 11, 2025

Commits on Mar 6, 2025

Commits on Mar 7, 2025