vLLM
/
vllm-project.github.io
mirror of https://github.com/vllm-project/vllm-project.github.io.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Minor 

Signed-off-by: WoosukKwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
WoosukKwon 2025-01-26 22:50:18 -08:00
parent 8f52fac61f
commit 4ff97a8f9d
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
_posts/2025-01-26-v1-alpha-release.md
View File

@ -128,7 +128,7 @@ We measured the performance of vLLM V0 and V1 on Llama 3.1 8B and Llama 3.3 70B
V1 demonstrated consistently lower latency than V0 especially at high QPS, thanks to the higher throughput it achieves. V1 demonstrated consistently lower latency than V0 especially at high QPS, thanks to the higher throughput it achieves.
Given that the kernels used for V0 and V1 are almost identical, the performance difference is mainly due to the architectural improvements (reduced CPU overheads) in V1. Given that the kernels used for V0 and V1 are almost identical, the performance difference is mainly due to the architectural improvements (reduced CPU overheads) in V1.
- **Vision-language Models: Qwen2-VL, 1xH100** - **Vision-language Models: Qwen2-VL**
<p align="center"> <p align="center">
<picture> <picture>