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, 00:30 UTC
[Misc] remove duplicate definition of `seq_lens_tensor` in model_runner.py (#5129)
Hyunsung Lee committed
May 30, 2024 at 22:56 UTC
d79d9eaaff90801668613a4e3d5d8a0004963f21
1 file changed
-3
vllm/worker/model_runner.py
-3
@@ -518,9 +518,6 @@ class ModelRunner:
518
else:
519
multi_modal_input = None
520
521
- seq_lens_tensor = torch.tensor(seq_lens,
522
- dtype=torch.int,
523
- device=self.device)
521
query_lens_tensor = torch.tensor(query_lens,
522
dtype=torch.long,
523
device=self.device)