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 17, 08:00 UTC
Fixed old name reference for max_seq_len
MoeedDar committed
Jul 18, 2023 at 16:47 UTC
328d231c17a6c414a40d6abf31c4deb410a750f8
1 file changed
+1
-1
vllm/core/scheduler.py
+1
-1
@@ -196,7 +196,7 @@ class Scheduler:
196
logger.warning(
197
f"Input prompt ({num_prompt_tokens} tokens) is too long"
198
" and exceeds limit of "
199
- f"{self.scheduler_config.max_seq_len}")
199
+ f"{self.scheduler_config.max_model_len}")
200
for seq in seq_group.get_seqs():
201
seq.status = SequenceStatus.FINISHED_IGNORED
202
ignored_seq_groups.append(seq_group)