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, 16:00 UTC
[Misc] Update compressed-tensors to version 0.9.3 (#16196)
Signed-off-by: Miles Williams <42222518+mlsw@users.noreply.github.com>
Miles Williams committed
Apr 8, 2025 at 03:09 UTC
f94ab12f792901f592f56f5c8727c72432fa29c2
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; 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 == 0.9.2 # required for compressed-tensors
39
+compressed-tensors == 0.9.3 # 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