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, 16:00 UTC
[Bugfix] Fix extra comma (#15851)
Signed-off-by: haochengxia <xhc_1007@163.com>
Percy committed
Apr 1, 2025 at 00:57 UTC
e830b01383d4c3372975e36aa068ac44eba90b9e
1 file changed
+1
-1
vllm/model_executor/sampling_metadata.py
+1
-1
@@ -191,7 +191,7 @@ class SamplingMetadata:
191
"SamplingMetadata("
192
f"seq_groups={self.seq_groups}, "
193
f"selected_token_indices={self.selected_token_indices}, "
194
- f"categorized_sample_indices={self.categorized_sample_indices}), ")
194
+ f"categorized_sample_indices={self.categorized_sample_indices})")
195
196
197
def _prepare_seq_groups(