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, 06:45 UTC
Fix quickstart.rst typo jinja (#1964)
gottlike committed
Dec 7, 2023 at 17:34 UTC
42c02f5892e984d308614f074f423a311aba8993
1 file changed
+1
-1
docs/source/getting_started/quickstart.rst
+1
-1
@@ -129,7 +129,7 @@ By default, the server uses a predefined chat template stored in the tokenizer.
129
130
$ python -m vllm.entrypoints.openai.api_server \
131
$ --model facebook/opt-125m \
132
- $ --chat-template ./examples/template_chatml.json
132
+ $ --chat-template ./examples/template_chatml.jinja
133
134
This server can be queried in the same format as OpenAI API. For example, list the models:
135