search

intel / neural-speed

An innovative library for efficient LLM inference via low-bit quantization
https://github.com/intel/neural-speed
Apache License 2.0
350 stars 38 forks source link

Revert max_load_vec_elems #323

Closed DDEle closed 3 months ago

DDEle commented 3 months ago

Type of Change: Fix

API not changed

Description

As title

Expected Behavior & Potential Risk

N/A

How has this PR been tested?

Internal IPEX CI

Dependency Change?

No

DDEle commented 3 months ago

Ready to merge as the internal IPEX PR merged.

sunjiweiswift commented 3 months ago

Thanks for Yi‘s help