PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Remove cuda UT dependencies version restrictions (#651)
Sun, Xuehao35cf154f22d4
diff --git a/test/test_cuda/requirements_vlm.txt b/test/test_cuda/requirements_vlm.txtindex cfe352536..0bfb0c39f 100644--- a/test/test_cuda/requirements_vlm.txt+++ b/test/test_cuda/requirements_vlm.txt@@ -3,21 +3,21 @@# pip install -v git+https://github.com/casper-hansen/[email protected] --no-build-isolationaccelerate# autoawq-bitsandbytes==0.44.0+bitsandbytesdatasetseinops-flash-attn==2.5.8+flash-attnintel-extension-for-transformerslm-eval>=0.4.2,<0.5numpy < 2.0optimumpandas-protobuf==3.20.2+protobufpillowpy-cpuinfo-torch==2.3.0+torchtorchvision-triton==2.3.0+tritontqdm-transformers==4.45.0+transformersxformers