LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Ecosystems
Launchpads

Python

production-stack

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

6mo ago

Recent commits

Latest commits.

[Feat] Router: Add OpenTelemetry tracing support with W3C context propagation
3215f7bFang Han6mo ago
Fix: Update nixlPeerHost to pd-llama-decode-engine-service (#771)
ab2c023Xunzhuo6mo ago
[Bugfix] Concurrent requests to model are currently limited to 100 due to aiohttp default (#767)
e3e0adbLevent K. (M.Sc.)6mo ago
[Docs] Correct parameter in transcription API tutorial (#685)
817d6b1David Gao6mo ago
fix(router): avoid startup race when scheduling sessions (#768)
eb9526fBernardo Donadio

6mo ago

Add responses endpoint for router (#691)

e1447afsebastiaanvduijn6mo ago

Add resources alternative to serving engine (#729)

b5c0f0fdanhubern7mo ago

Add production-ready vLLM Nebius MK8s terraform stack (#748)

f2651a2Clouddude7mo ago

Top contributors

Builders behind this project.