@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f0e0238016
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 16, 07:00 UTC

[Doc] fix a small typo in docstring of llama_tool_parser (#10513)

Zhong Qishuai committed Nov 21, 2024 at 17:05 UTC f0e02380169b99a20cc5a4cd1848bbe085b50d5c
1 file changed +2 -1
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py
+2 -1
@@ -29,7 +29,8 @@ class Llama3JsonToolParser(ToolParser):
29 Tool call parser for Llama 3.1 models intended for use with the
30 examples/tool_chat_template_llama.jinja template.
31
32 - Used when --enable-auto-tool-choice --tool-call-parser mistral are all set
32 + Used when --enable-auto-tool-choice --tool-call-parser llama3_json
33 + are all set
34 """
35
36 def __init__(self, tokenizer: PreTrainedTokenizerBase):