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 14, 23:45 UTC
[Misc] Refactor vllm config str (#21666)
Ning Xie committed
Jul 28, 2025 at 00:51 UTC
a9b2a1d7048c7129ee6f55af68624256da864fed
1 file changed
+12
-12
vllm/config.py
+12
-12
@@ -4790,26 +4790,26 @@ class VllmConfig:
4790
4791
def __str__(self):
4792
return (
4793
- f"model={self.model_config.model!r},"
4794
- f" speculative_config={self.speculative_config!r},"
4795
- f" tokenizer={self.model_config.tokenizer!r}, "
4796
- f"skip_tokenizer_init={self.model_config.skip_tokenizer_init},"
4797
- f" tokenizer_mode={self.model_config.tokenizer_mode}, "
4793
+ f"model={self.model_config.model!r}, "
4794
+ f"speculative_config={self.speculative_config!r}, "
4795
+ f"tokenizer={self.model_config.tokenizer!r}, "
4796
+ f"skip_tokenizer_init={self.model_config.skip_tokenizer_init}, "
4797
+ f"tokenizer_mode={self.model_config.tokenizer_mode}, "
4798
f"revision={self.model_config.revision}, "
4799
- f"override_neuron_config={self.model_config.override_neuron_config},"
4800
- f" tokenizer_revision={self.model_config.tokenizer_revision}, "
4799
+ f"override_neuron_config={self.model_config.override_neuron_config}, " # noqa
4800
+ f"tokenizer_revision={self.model_config.tokenizer_revision}, "
4801
f"trust_remote_code={self.model_config.trust_remote_code}, "
4802
f"dtype={self.model_config.dtype}, "
4803
- f"max_seq_len={self.model_config.max_model_len},"
4804
- f" download_dir={self.load_config.download_dir!r}, "
4803
+ f"max_seq_len={self.model_config.max_model_len}, "
4804
+ f"download_dir={self.load_config.download_dir!r}, "
4805
f"load_format={self.load_config.load_format}, "
4806
- f"tensor_parallel_size={self.parallel_config.tensor_parallel_size},"
4807
- f" pipeline_parallel_size={self.parallel_config.pipeline_parallel_size}, " # noqa
4806
+ f"tensor_parallel_size={self.parallel_config.tensor_parallel_size}, " # noqa
4807
+ f"pipeline_parallel_size={self.parallel_config.pipeline_parallel_size}, " # noqa
4808
f"disable_custom_all_reduce={self.parallel_config.disable_custom_all_reduce}, " # noqa
4809
f"quantization={self.model_config.quantization}, "
4810
f"enforce_eager={self.model_config.enforce_eager}, "
4811
f"kv_cache_dtype={self.cache_config.cache_dtype}, "
4812
- f" device_config={self.device_config.device}, "
4812
+ f"device_config={self.device_config.device}, "
4813
f"decoding_config={self.decoding_config!r}, "
4814
f"observability_config={self.observability_config!r}, "
4815
f"seed={self.model_config.seed}, "