Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

temporary pin compressed-tensors version for llmcompressor (#1560)

chen, suyue3a8c26e602e9
diff --git a/test/test_cpu/requirements.txt b/test/test_cpu/requirements.txt
index a6ce699a7..367f0ffd8 100644
--- a/test/test_cpu/requirements.txt
+++ b/test/test_cpu/requirements.txt
@@ -6,6 +6,7 @@ torchvision
pillow
numba
llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@main
+compressed-tensors==0.14.1a20260313 # temporary pin for llmcompressor
lm_eval >= 0.4.10 # for transformers >= 5.0.0
diffusers
protobuf
diff --git a/test/test_cuda/requirements_llmc.txt b/test/test_cuda/requirements_llmc.txt
index b11e53b7a..c82328a23 100644
--- a/test/test_cuda/requirements_llmc.txt
+++ b/test/test_cuda/requirements_llmc.txt
@@ -1,2 +1,3 @@
llmcompressor @ git+https://github.com/vllm-project/llm-compressor.git@main
+compressed-tensors==0.14.1a20260313 # temporary pin for llmcompressor
parameterized