A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 04:45 UTC
[Quantization] Bump to use latest `compressed-tensors` (#20033)
Signed-off-by: Dipika <dipikasikka1@gmail.com> Co-authored-by: Kyle Sayers <kylesayrs@gmail.com>
Dipika Sikka committed
Jun 26, 2025 at 23:50 UTC
a57d57fa72f092b9b8ed8415553ec02609daa644
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -37,7 +37,7 @@ pyyaml
37
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
38
setuptools>=77.0.3,<80; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
39
einops # Required for Qwen2-VL.
40
-compressed-tensors == 0.10.1 # required for compressed-tensors
40
+compressed-tensors == 0.10.2 # required for compressed-tensors
41
depyf==0.18.0 # required for profiling and debugging with compilation config
42
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
43
watchfiles # required for http server to monitor the updates of TLS files