jmaczan/tiny-vllm

tiny-vllm

✅ Recently maintained

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

1,180Stars
102Forks
+117-day stars

C++ · Apache-2.0 · Last push 2026-11-01

Official repository & installation ↗

Star history

2026-02-092026-11-02
View historical data
DateStars
2026-10-041,140
2026-10-051,141
2026-10-061,143
2026-10-071,144
2026-10-081,146
2026-10-091,147
2026-10-101,147
2026-10-111,148
2026-10-121,150
2026-10-131,151
2026-10-141,151
2026-10-151,151
2026-10-161,152
2026-10-171,154
2026-10-181,156
2026-10-191,156
2026-10-201,157
2026-10-211,160
2026-10-221,162
2026-10-231,162
2026-10-241,166
2026-10-251,168
2026-10-261,170
2026-10-271,172
2026-10-281,173
2026-10-291,174
2026-10-301,175
2026-10-311,178
2026-11-011,180
2026-11-021,180

Get the project

git clone https://github.com/jmaczan/tiny-vllm.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.