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, 21:00 UTC
[V1][Minor] Restore V1 compatibility with LLMEngine class (#13090)
Thibault Schueller committed
Feb 28, 2025 at 09:52 UTC
b3f7aaccd0338e86dc58a6c7ea867a43be9a591b
1 file changed
+5
vllm/engine/llm_engine.py
+5
@@ -2084,3 +2084,8 @@ class LLMEngine:
2084
sampling_params.logits_processors.extend(logits_processors)
2085
2086
return sampling_params
2087
+
2088
+
2089
+# TODO(v1): Remove this class proxy when V1 goes default.
2090
+if envs.VLLM_USE_V1:
2091
+ from vllm.v1.engine.llm_engine import LLMEngine # type: ignore