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 16, 00:45 UTC
Update compressed-tensors version (#12367)
Dipika Sikka committed
Jan 23, 2025 at 22:19 UTC
55ef66edf48a15468a96cb34985319c57e3840ce
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -34,6 +34,6 @@ pyyaml
34
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
35
setuptools>=74.1.1; 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
36
einops # Required for Qwen2-VL.
37
-compressed-tensors == 0.8.1 # required for compressed-tensors
37
+compressed-tensors == 0.9.0 # required for compressed-tensors
38
depyf==0.18.0 # required for profiling and debugging with compilation config
39
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py