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, 04:45 UTC
[Chore] debloat some initial logs (#19438)
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Aaron Pham committed
Jun 25, 2025 at 02:36 UTC
ba7ba35cdaeacb59860bad2691de190bd77ccd05
1 file changed
+4
-4
vllm/config.py
+4
-4
@@ -546,10 +546,10 @@ class ModelConfig:
546
self.code_revision, self.config_format)
547
548
if hf_overrides_kw:
549
- logger.info("Overriding HF config with %s", hf_overrides_kw)
549
+ logger.debug("Overriding HF config with %s", hf_overrides_kw)
550
hf_config.update(hf_overrides_kw)
551
if hf_overrides_fn:
552
- logger.info("Overriding HF config with %s", hf_overrides_fn)
552
+ logger.debug("Overriding HF config with %s", hf_overrides_fn)
553
hf_config = hf_overrides_fn(hf_config)
554
555
self.hf_config = hf_config
@@ -1947,8 +1947,8 @@ class ParallelConfig:
1947
if get_current_placement_group():
1948
backend = "ray"
1949
self.distributed_executor_backend = backend
1950
- logger.info("Defaulting to use %s for distributed inference",
1951
- backend)
1950
+ logger.debug("Defaulting to use %s for distributed inference",
1951
+ backend)
1952
1953
if self.distributed_executor_backend is None and self.world_size == 1:
1954
self.distributed_executor_backend = "uni"