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
fix: typo (#948)
Wen Sun committed
Sep 5, 2023 at 14:22 UTC
22379d55130cb3c8d8c2130eedc0eaedf5e209e1
1 file changed
+1
-1
vllm/engine/async_llm_engine.py
+1
-1
@@ -81,7 +81,7 @@ class _AsyncLLMEngine(LLMEngine):
81
blocks_to_copy=scheduler_outputs.blocks_to_copy,
82
)
83
84
- return self._process_worker_outputs(output, scheduler_outputs)
84
+ return self._process_model_outputs(output, scheduler_outputs)
85
86
async def _run_workers_async(
87
self,