The Gateway Index / Routers / #111
megeezy/Chameleon
by megeezy · Routers · updated 2mo ago
Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent model selection.
46
momentum
42
stars
2
forks
#111
rank
ai-infrastructuregenerative-ailatency-optimizationllmmodel-routingmodel-schedulingsystems-programmingvram-optimization
View on GitHub →