Code Stars
2.31K subscribers
12.6K photos
12.9K links
Track GitHub repos gaining stars in real time. Discover trending projects in AI, Python, JavaScript, React, and DevOps before they go viral. Updated hourly.
Download Telegram
jmaczan/tiny-vllm
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
Language:C++
Total stars: 525
Stars trend:
30 May 2026
5am ▉ +7
6am ▌ +4
7am ▌ +4
8am ▌ +4
9am ▎ +2
10am ▎ +2
11am ▏ +1
12pm ▍ +3

#cplusplus
#ai, #attention, #batching, #course, #cpp, #cuda, #hpc, #inference, #llm, #llminference, #pagedattention, #tinyvllm, #vllm
1