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, 12:15 UTC
Bump Compressed Tensors version to 0.9.4 (#17478)
Signed-off-by: Rahul Tuli <rtuli@redhat.com> Co-authored-by: mgoin <mgoin64@gmail.com>
Rahul Tuli committed
Apr 30, 2025 at 17:24 UTC
200bbf92e8861e2458a6f90bca73f40cc3b1ad1f
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -36,7 +36,7 @@ pyyaml
36
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
37
setuptools>=74.1.1,<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
38
einops # Required for Qwen2-VL.
39
-compressed-tensors == 0.9.3 # required for compressed-tensors
39
+compressed-tensors == 0.9.4 # required for compressed-tensors
40
depyf==0.18.0 # required for profiling and debugging with compilation config
41
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
42
watchfiles # required for http server to monitor the updates of TLS files