Update llm-api-benchmark

This commit is contained in:
FlintyLemming 2025-04-05 01:00:29 +08:00
parent f61999ccb2
commit 9464c2e933

View File

@ -142,4 +142,4 @@ python vllm_benchmark.py --token-lengths 10 100 500 1000 2000 5000 10000 20000 3
![](src/success_rate_vs_concurrency.png) ![](src/success_rate_vs_concurrency.png)
![](total_tokens_per_second_vs_concurrency.png) ![](src/total_tokens_per_second_vs_concurrency.png)