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 7, 19:00 UTC
[Docs]Fix documentation formatting in architecture overview (#34679)
Signed-off-by: codedump <lichuang1982@gmail.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
lichuang committed
Feb 25, 2026 at 16:00 UTC
2c619e5e3f3b5712073546d10b10f1a2f00ce5a4
1 file changed
+1
-3
docs/design/arch_overview.md
+1
-3
@@ -208,9 +208,7 @@ configurations affect the class we ultimately get.
208
209
The following figure shows the class hierarchy of vLLM:
210
211
-> <figure markdown="span">
212
-> { align="center" alt="query" width="100%" }
213
-> </figure>
211
+
212
213
There are several important design choices behind this class hierarchy:
214