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, 13:30 UTC
[V1] Remove additional_config check (#16710)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
wangxiyuan committed
Apr 22, 2025 at 11:45 UTC
b9b47469507c44fa7a1330bfcaaf05951bb444c3
1 file changed
-5
vllm/engine/arg_utils.py
-5
@@ -1361,11 +1361,6 @@ class EngineArgs:
1361
recommend_to_remove=True)
1362
return False
1363
1364
- if self.additional_config != EngineArgs.additional_config:
1365
- _raise_or_fallback(feature_name="--additional-config",
1366
- recommend_to_remove=False)
1367
- return False
1368
-
1364
# Xgrammar and Guidance are supported.
1365
SUPPORTED_GUIDED_DECODING = [
1366
"xgrammar", "xgrammar:disable-any-whitespace", "guidance",