Skip to content

Commit a4dbdd2

Browse files
tdoubleprasmith
authored andcommitted
Remove pytorch comments for outlines + compressed-tensors (vllm-project#12260)
Signed-off-by: Thomas Parnell <[email protected]>
1 parent 0a9ed57 commit a4dbdd2

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

requirements-common.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ pillow # Required for image processing
1919
prometheus-fastapi-instrumentator >= 7.0.0
2020
tiktoken >= 0.6.0 # Required for DBRX tokenizer
2121
lm-format-enforcer >= 0.10.9, < 0.11
22-
outlines == 0.1.11 # Requires pytorch
22+
outlines == 0.1.11
2323
lark == 1.2.2
2424
xgrammar >= 0.1.6; platform_machine == "x86_64"
2525
typing_extensions >= 4.10
@@ -34,6 +34,6 @@ pyyaml
3434
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
3535
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
3636
einops # Required for Qwen2-VL.
37-
compressed-tensors == 0.8.1 # required for compressed-tensors, requires pytorch
37+
compressed-tensors == 0.8.1 # required for compressed-tensors
3838
depyf==0.18.0 # required for profiling and debugging with compilation config
3939
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py

0 commit comments

Comments
 (0)