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

[Bug]fix glm4 acc error #294

Closed intellinjun closed 5 months ago

intellinjun commented 5 months ago

image glm4-9b-chat q4j32 result