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, 04:30 UTC
update compressed-tensors to latest version (#11183)
Co-authored-by: dhuangnm <dhuang@MacBook-Pro-2.local>
dhuangnm committed
Dec 13, 2024 at 22:22 UTC
24a3d12b821a081850c1659f61762e799eeba902
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -33,5 +33,5 @@ pyyaml
33
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
34
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
35
einops # Required for Qwen2-VL.
36
-compressed-tensors == 0.8.0 # required for compressed-tensors
36
+compressed-tensors == 0.8.1 # required for compressed-tensors
37
depyf==0.18.0 # required for profiling and debugging torch.compile