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, 17:15 UTC
[Misc] Update guided decoding logs to debug (#15310)
Signed-off-by: Benjamin Merkel <benjamin.merkel@tngtech.com> Co-authored-by: Benjamin Merkel <benjamin.merkel@tngtech.com>
sfbemerk committed
Mar 24, 2025 at 12:25 UTC
cc8accfd5344f5eeadb6a388a56f662b7b1d1bbc
1 file changed
+1
-1
vllm/engine/async_llm_engine.py
+1
-1
@@ -545,7 +545,7 @@ async def build_guided_decoding_logits_processor_async(
545
sampling_params = copy.copy(sampling_params)
546
guided_decoding = sampling_params.guided_decoding
547
548
- logger.info(
548
+ logger.debug(
549
"Building guided decoding logits processor. "
550
"guided_decoding: %s%s", guided_decoding,
551
f", reasoning_backend: {reasoning_backend}"