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 4, 13:45 UTC
[Core] Fix redundant None append in StepPool.forward for chunked prefill (#41049)
Signed-off-by: Anthony Su <xsuanthony@gmail.com>
anthonsu committed
Apr 27, 2026 at 23:42 UTC
76c9cccc368fde7f1b8d8a546e3638f4f434c8fd
1 file changed
+1
-1
vllm/model_executor/layers/pooler/tokwise/methods.py
+1
-1
@@ -111,7 +111,7 @@ class StepPool(AllPool):
111
if step_tag_id is not None:
112
data = data[token_id == step_tag_id]
113
114
- pooled_data.append(data)
114
+ pooled_data.append(data)
115
116
return pooled_data
117