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 12, 11:00 UTC
[Bugfix] Fix doc build on main (#29619)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Nov 28, 2025 at 01:08 UTC
ee9841daa995a606139775043f0199d6a81037b3
1 file changed
+1
-2
vllm/model_executor/models/interfaces_base.py
+1
-2
@@ -167,8 +167,7 @@ class VllmModelForPooling(VllmModel[T_co], Protocol[T_co]):
167
168
default_pooling_type: ClassVar[str] = "LAST"
169
"""
170
- Indicates the
171
- [vllm.model_executor.layers.pooler.PoolerConfig.pooling_type][]
170
+ Indicates the [vllm.config.pooler.PoolerConfig.pooling_type][]
171
to use by default.
172
173
You can use the