biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)

Browse Source 
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
This commit is contained in:
Sanger Steel
2025-05-22 21:44:18 -04:00
committed by GitHub
parent c91fe7b1b9
commit c32e249a23
16 changed files with 606 additions and 197 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/engine/arg_utils.py
View File

@@ -1195,8 +1195,7 @@ class EngineArgs:
#############################################################
# Unsupported Feature Flags on V1.
if (self.load_format == LoadFormat.TENSORIZER.value
or self.load_format == LoadFormat.SHARDED_STATE.value):
if self.load_format == LoadFormat.SHARDED_STATE.value:
_raise_or_fallback(
feature_name=f"--load_format {self.load_format}",
recommend_to_remove=False)