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
[build][torch.compile] upgrade depyf version (#26702)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Oct 14, 2025 at 10:12 UTC
8a0af6a5610b7eb6232bc5f66fda40a46b275869
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -39,7 +39,7 @@ six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that need
39
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
40
einops # Required for Qwen2-VL.
41
compressed-tensors == 0.12.2 # required for compressed-tensors
42
-depyf==0.19.0 # required for profiling and debugging with compilation config
42
+depyf==0.20.0 # required for profiling and debugging with compilation config
43
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
44
watchfiles # required for http server to monitor the updates of TLS files
45
python-json-logger # Used by logging as per examples/others/logging_configuration.md