The Gateway Index / Routers / #216
megeezy/Chameleon
by megeezy · Routers · updated 5mo ago
Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent model selection.
19
momentum
42
stars
3
forks
#216
rank
ai-infrastructuregenerative-ailatency-optimizationllmmodel-routingmodel-schedulingsystems-programmingvram-optimization
View on GitHub →