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, 22:15 UTC
[CI/Build] force writing version file (#13544)
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
Daniele committed
Feb 19, 2025 at 11:48 UTC
81dabf24a837ced3f4fc6131e8a7c99a63e646a5
2 files changed
+2
-2
pyproject.toml
+1
-1
@@ -42,7 +42,7 @@ Slack="http://slack.vllm.ai/"
42
vllm = "vllm.entrypoints.cli.main:main"
43
44
[tool.setuptools_scm]
45
-version_file = "vllm/_version.py"
45
+# no extra settings needed, presence enables setuptools-scm
46
47
[tool.setuptools.packages.find]
48
where = ["."]
setup.py
+1
-1
@@ -499,7 +499,7 @@ def get_gaudi_sw_version():
499
500
501
def get_vllm_version() -> str:
502
- version = get_version()
502
+ version = get_version(write_to="vllm/_version.py")
503
sep = "+" if "+" not in version else "." # dev versions might contain +
504
505
if _no_device():