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

change acknowledgement

This commit is contained in:
Zhuohan Li 2024-09-05 09:48:33 -07:00
parent 67d2c32341
commit fadcbcc3cd
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/2024-09-05-perf-update.md
View File

@ -152,7 +152,7 @@ Regardless where you are, don’t forget to sign up for the online [biweekly vLL
### Acknowledgment
The blogpost is drafted by the vLLM team at UC Berkeley. The performance boost comes from collective efforts in the vLLM community: [Robert Shaw](https://github.com/robertgshaw2-neuralmagic) from Neural Magic and [Nick Hill](https://github.com/njhill), [Joe Runde](https://github.com/joerunde) from IBM lead the API server refactoring, [Will Lin](https://github.com/SolitaryThinker) from UCSD and [Cody Yu](https://github.com/comaniac) from Anyscale lead the multi-step scheduling effort, [Megha Agarwal](https://github.com/megha95) from Databricks and [Alexander Matveev](https://github.com/alexm-neuralmagic) from Neural Magic lead the async output processing, and many contributors from the vLLM community contribute various optimizations. All these efforts bring us together to get a significant performance boost.
The blogpost is drafted by the vLLM team at Berkeley. The performance boost comes from collective efforts in the vLLM community: [Robert Shaw](https://github.com/robertgshaw2-neuralmagic) from Neural Magic and [Nick Hill](https://github.com/njhill), [Joe Runde](https://github.com/joerunde) from IBM lead the API server refactoring, [Will Lin](https://github.com/SolitaryThinker) from UCSD and [Antoni Baum](https://github.com/Yard1), [Cody Yu](https://github.com/comaniac) from Anyscale lead the multi-step scheduling effort, [Megha Agarwal](https://github.com/megha95) from Databricks and [Alexander Matveev](https://github.com/alexm-neuralmagic) from Neural Magic lead the async output processing, and many contributors from the vLLM community contribute various optimizations. All these efforts bring us together to get a huge performance boost.
## Appendix