← Back to Leaderboard
Project comparison
vLLM vs llama.cpp
Compare adoption, momentum, maintenance health, and project basics before choosing which tool to evaluate deeper.
vLLM
A high-throughput and memory-efficient inference and serving engine for LLMs
79.7K
Stars
+606
Weekly
93/100
Health
llama.cpp
LLM inference in C/C++
109.6K
Stars
+1.2K
Weekly
100/100
Health
Quick Take
Adoption
llama.cpp has the larger GitHub footprint with 109.6K stars.
Momentum
llama.cpp is currently growing faster at +1.2K stars this week.
Maintenance
llama.cpp has the stronger health score at 100/100.
Side-by-side Metrics
| Signal | vLLM | llama.cpp |
|---|---|---|
| GitHub stars | 79.7K | 109.6K |
| Weekly growth | +606 | +1.2K |
| Health score | 93 | 100 |
| Contributors | 2.6K | 1.7K |
| Commits per week | 208.8 | 86.2 |
| Open issues | 4.9K | 1.6K |
| Language | Python | C++ |
| License | Apache-2.0 | MIT |
| Last commit | 13h ago | 14h ago |
| Last release | v0.20.2 | b9113 |
Weekly AI open-source movers
Get the fastest-growing projects, useful MCP servers, and technical reads in one weekly email.