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 13, 20:45 UTC
[Core] Enable StatLogger in LLMEngine (#28020)
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Zhuohan Li committed
Nov 4, 2025 at 04:13 UTC
300a2659785fb925f347637d5639d74cc2c5a9f5
1 file changed
-5
vllm/v1/engine/llm_engine.py
-5
@@ -58,11 +58,6 @@ class LLMEngine:
58
use_cached_outputs: bool = False,
59
multiprocess_mode: bool = False,
60
) -> None:
61
- if stat_loggers is not None:
62
- raise NotImplementedError(
63
- "Passing StatLoggers to LLMEngine is not yet supported."
64
- )
65
-
61
self.vllm_config = vllm_config
62
self.observability_config = vllm_config.observability_config
63
self.model_config = vllm_config.model_config