PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
add llmc for cuda ut (#1145)
Yi Liu2aeffe78aa02
diff --git a/test/test_cpu/requirements.txt b/test/test_cpu/requirements.txtindex cfa43463c..219189829 100644--- a/test/test_cpu/requirements.txt+++ b/test/test_cpu/requirements.txt@@ -6,6 +6,5 @@ torchvisionparameterizedpillownumba-#TODO: (yiliu30) replace it with the release versionllmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@mainlm_eval\ No newline at end of filediff --git a/test/test_cuda/requirements.txt b/test/test_cuda/requirements.txtindex 6cdc59633..86c0435c7 100644--- a/test/test_cuda/requirements.txt+++ b/test/test_cuda/requirements.txt@@ -13,4 +13,4 @@ pillowtorchvisionnumbavllm>=0.8.5.post1-compressed-tensors+llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@main\ No newline at end of file