@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 9c7306ac11
Fork 0

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 17, 01:45 UTC

[Misc] fix typo in llm_engine init logging (#4428)

DefTruth committed Apr 28, 2024 at 18:58 UTC 9c7306ac114da3e31a5ff040a76f6c640354cce8
1 file changed +1 -1
vllm/engine/llm_engine.py
+1 -1
@@ -101,7 +101,7 @@ class LLMEngine:
101 "skip_tokenizer_init=%s, tokenizer_mode=%s, revision=%s, "
102 "tokenizer_revision=%s, trust_remote_code=%s, dtype=%s, "
103 "max_seq_len=%d, download_dir=%r, load_format=%s, "
104 - "tensor_parallel_size=%d, disable_custom_all_reduce=%s"
104 + "tensor_parallel_size=%d, disable_custom_all_reduce=%s, "
105 "quantization=%s, enforce_eager=%s, kv_cache_dtype=%s, "
106 "quantization_param_path=%s, device_config=%s, "
107 "decoding_config=%r, seed=%d)",