PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Freeze compressed-tensors & llmc version temporary (#1562)
chen, suyue4cc0cce4b5d0
diff --git a/test/test_cpu/requirements.txt b/test/test_cpu/requirements.txtindex 367f0ffd8..80f981849 100644--- a/test/test_cpu/requirements.txt+++ b/test/test_cpu/requirements.txt@@ -5,7 +5,7 @@ sentencepiecetorchvisionpillownumba-llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@main+llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@370c04c34191c0e5fb88cf889e16578bf8c7fe20compressed-tensors==0.14.1a20260313 # temporary pin for llmcompressorlm_eval >= 0.4.10 # for transformers >= 5.0.0diffusersdiff --git a/test/test_cuda/requirements_llmc.txt b/test/test_cuda/requirements_llmc.txtindex c82328a23..d03556a6b 100644--- a/test/test_cuda/requirements_llmc.txt+++ b/test/test_cuda/requirements_llmc.txt@@ -1,3 +1,3 @@-llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@main+llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@370c04c34191c0e5fb88cf889e16578bf8c7fe20compressed-tensors==0.14.1a20260313 # temporary pin for llmcompressorparameterized