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] Benchmark Serving Incorrect Arg (#25474)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
vllmellm committed
Sep 23, 2025 at 21:05 UTC
0d9fe260dda994646b1e74f424b2c5e32190a78f
1 file changed
+2
-2
docs/contributing/benchmarks.md
+2
-2
@@ -680,7 +680,7 @@ vllm bench serve \
680
--save-result \
681
--result-dir ~/vllm_benchmark_results \
682
--save-detailed \
683
- --endpoint /v1/chat/completion
683
+ --endpoint /v1/chat/completions
684
```
685
686
##### Videos (ShareGPT4Video)
@@ -707,7 +707,7 @@ vllm bench serve \
707
--save-result \
708
--result-dir ~/vllm_benchmark_results \
709
--save-detailed \
710
- --endpoint /v1/chat/completion
710
+ --endpoint /v1/chat/completions
711
```
712
713
##### Synthetic Random Images (random-mm)