Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

lumia431/photon_infer

A High-Performance LLM Inference Engine with vLLM-Style Continuous Batching

Owner
lumia431 (personal account)
Stars
Stars: 122
Forks
Forks: 7
Language
C++
License
MIT
Created
2025
Topics
ai-infracontinuous-batchinginference-enginellm-inferencemodern-cpppaged-attentionvllm
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by lumia431

All 2 repos by lumia431

Nearby in C++

All C++ repos