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 14, 05:30 UTC
[Quantization] Bump Compressed Tensors Version (#23202)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
Kyle Sayers committed
Aug 19, 2025 at 20:39 UTC
c32e6ad1f63631fd8033f0cca3a35d5e48ccfc7f
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -39,7 +39,7 @@ pyyaml
39
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
40
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
41
einops # Required for Qwen2-VL.
42
-compressed-tensors == 0.10.2 # required for compressed-tensors
42
+compressed-tensors == 0.11.0 # required for compressed-tensors
43
depyf==0.19.0 # required for profiling and debugging with compilation config
44
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
45
watchfiles # required for http server to monitor the updates of TLS files