PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Bump protobuf from 3.20.1 to 3.20.2 in /test/test_cuda (#585)
dependabot[bot]dc6d389545d8
diff --git a/test/test_cuda/requirements_vlm.txt b/test/test_cuda/requirements_vlm.txtindex ee7b3e5de..cfe352536 100644--- a/test/test_cuda/requirements_vlm.txt+++ b/test/test_cuda/requirements_vlm.txt@@ -12,7 +12,7 @@ lm-eval>=0.4.2,<0.5numpy < 2.0optimumpandas-protobuf==3.20.1+protobuf==3.20.2pillowpy-cpuinfotorch==2.3.0