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
2.18k stars 252 forks source link

update 3x torch installation #1957

Closed chensuyue closed 2 months ago

chensuyue commented 2 months ago

Type of Change

update 3x torch installation

Description

provide multiple torch install choice for different platform

Expected Behavior & Potential Risk

CI pass

How has this PR been tested?

CI

Dependency Change?

No