From 8d2cf38c796c501f99b2f4d2413b04ba03bb8ae9 Mon Sep 17 00:00:00 2001 From: Lianmin Zheng Date: Mon, 14 Jul 2025 10:55:13 -0700 Subject: [PATCH] [Minor] Remove redundant print (#8005) --- python/sglang/srt/hf_transformers_utils.py | 1 - python/sglang/srt/layers/vocab_parallel_embedding.py | 2 -- 2 files changed, 3 deletions(-) diff --git a/python/sglang/srt/hf_transformers_utils.py b/python/sglang/srt/hf_transformers_utils.py index e5b4af0c3..7c056acdd 100644 --- a/python/sglang/srt/hf_transformers_utils.py +++ b/python/sglang/srt/hf_transformers_utils.py @@ -167,7 +167,6 @@ def get_generation_config( model, trust_remote_code=trust_remote_code, revision=revision, **kwargs ) except OSError as e: - logging.info("model doesn't have generation_config.json") return None diff --git a/python/sglang/srt/layers/vocab_parallel_embedding.py b/python/sglang/srt/layers/vocab_parallel_embedding.py index e7a8ebe11..0e075a251 100644 --- a/python/sglang/srt/layers/vocab_parallel_embedding.py +++ b/python/sglang/srt/layers/vocab_parallel_embedding.py @@ -569,8 +569,6 @@ class ParallelLMHead(VocabParallelEmbedding): if _is_cpu and _is_cpu_amx_available: if hasattr(self, "weight") and self.weight.dtype == torch.bfloat16: self.quant_method = PackWeightMethod(weight_names=["weight"]) - else: - logger.warning("The weight of LmHead is not packed") if bias: self.bias = Parameter(