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, 05:30 UTC
[Docs] Fix an admonition important (#23726)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
Michael Yao committed
Aug 27, 2025 at 17:50 UTC
5bd9f841581a3a9e9eecdd8764240575bb28e391
1 file changed
+1
-1
docs/configuration/optimization.md
+1
-1
@@ -164,7 +164,7 @@ llm = LLM(
164
)
165
```
166
167
-!! important
167
+!!! important
168
Batch-level DP is not to be confused with API request-level DP
169
(which is instead controlled by `data_parallel_size`).
170