search

intel / neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
https://intel.github.io/neural-compressor/
Apache License 2.0
2.23k stars 257 forks source link

new results or previous results could not find all raise issues in CI model test #1958

Closed chensuyue closed 3 months ago

chensuyue commented 3 months ago

Type of Change

validation update

Description

New results or previous results could not find all raise issues in CI model test, so the test will raise accuracy regression on time.

Expected Behavior & Potential Risk

the expected behavior that triggered by this PR

How has this PR been tested?

how to reproduce the test (including hardware information)

Dependency Change?

any library dependency introduced or removed