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 6, 09:30 UTC
[Bug] Fix EmbedIOprocessor "classify" <-> "embed" (#37573)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Mar 19, 2026 at 19:40 UTC
df3c0291a3d6aceb0e1393ab0bdbd16dec9f2081
1 file changed
+1
-1
vllm/entrypoints/pooling/io_processor_factories.py
+1
-1
@@ -23,7 +23,7 @@ def init_pooling_io_processors(
23
if "embed" in supported_tasks:
24
from vllm.entrypoints.pooling.embed.io_processor import EmbedIOProcessor
25
26
- processors.append(("classify", EmbedIOProcessor))
26
+ processors.append(("embed", EmbedIOProcessor))
27
28
return {
29
task: processor_cls(