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, 23:30 UTC
[Bugfix] Remove unused seq_group_metadata_list from ModelInputForGPU (#12935)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
shangmingc committed
Feb 8, 2025 at 22:46 UTC
913df14da3014d9432bfd8a5114f845ab567b1c6
1 file changed
-1
vllm/worker/model_runner.py
-1
@@ -98,7 +98,6 @@ class ModelInputForGPU(ModelRunnerInputBase):
98
finished_requests_ids: Optional[List[str]] = None
99
virtual_engine: int = 0
100
async_callback: Optional[Callable] = None
101
- seq_group_metadata_list: Optional[List[SequenceGroupMetadata]] = None
101
scheduler_outputs: Optional[SchedulerOutputs] = None
102
103
def as_broadcastable_tensor_dict(self) -> Dict[str, Any]: