PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
update README.md (#32)
chen, suyue514aa493734e
diff --git a/README.md b/README.mdindex b6da0240a..7d7e05605 100644--- a/README.md+++ b/README.md@@ -21,6 +21,10 @@ AutoRound is an advanced weight-only quantization algorithm for low-bits LLM infpip install -r requirements.txtpython setup.py install```+### Install from pypi+```bash+pip install auto-round+```## Usage of Tuning### On CPU/ Gaudi2/ GPU@@ -181,11 +185,6 @@ We provide a [comprehensive analysis](docs/acc.md) with other methods in our acc3 Setting 'minmax_lr' to 2.0/iters has been observed to occasionally yield improved results.--## Examples-Quantization has been enabled for various large language models. Please refer to the [example readme](examples/README.md) for details.--## ReferenceIf you find SignRound useful for your research, please cite our paper:```bash