xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-09-04 04:26:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Don't default construct ModelConfig when default constructing VllmConfig (#17943)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-05-10 14:23:00 +01:00 committed by GitHub
parent fc4441a4ee
commit 68311891f5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/config.py
View File

@ -3954,7 +3954,9 @@ class VllmConfig:
simplifies passing around the distinct configurations in the codebase. simplifies passing around the distinct configurations in the codebase.
""" """
model_config: ModelConfig = field(default_factory=ModelConfig) # TODO: use default_factory once default constructing ModelConfig doesn't
# try to download a model
model_config: ModelConfig = None # type: ignore
"""Model configuration.""" """Model configuration."""
cache_config: CacheConfig = field(default_factory=CacheConfig) cache_config: CacheConfig = field(default_factory=CacheConfig)
"""Cache configuration.""" """Cache configuration."""