scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

docs /v1/messages

Browse source
This commit is contained in:
Ishaan Jaff 2025-06-07 12:28:25 -07:00
parent 5c63d86b58
commit a99cae867d
2 changed files with 10 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

BIN
docs/my-website/img/release_notes/v1_messages_perf.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 515 KiB

10
docs/my-website/release_notes/v1.72.2/index.md
View file

@ -66,6 +66,16 @@ pip install litellm==1.72.2
---
## `/v1/messages` Performance Improvements
This release brings significant performance improvements to the `/v1/messages` API. For large streaming requests LiteLLM overhead latency is now 50ms and can handle 250 RPS per instance.
<Image
img={require('../../img/release_notes/v1_messages_perf.png')}
style={{width: '100%', display: 'block', margin: '2rem auto'}}
/>
## New Models / Updated Models
**Newly Added Models**