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, 06:45 UTC
[Fix] Remove false assertion (#1222)
Woosuk Kwon committed
Sep 28, 2023 at 10:52 UTC
2e8e49fce3775e7704d413b2f02da6d7c99525c9
1 file changed
-2
vllm/worker/worker.py
-2
@@ -155,8 +155,6 @@ class Worker:
155
self,
156
seq_group_metadata_list: List[SequenceGroupMetadata],
157
) -> Tuple[torch.Tensor, torch.Tensor, InputMetadata]:
158
- assert self.block_size is not None
159
-
158
seq_groups: List[Tuple[List[int], SamplingParams]] = []
159
input_tokens: List[int] = []
160
input_positions: List[int] = []