jmaczan/tiny-vllm

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

C++

1.2k

106

1 contributors

Apache License 2.0

FeaturedAdvertise to 180K+ monthly visitors

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast jmaczan/tiny-vllm is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 6 – Nov 5, 2026

Stars +85 in 61 days

4

Forks +14 in 61 days

2

Merged PRs 6 in 61 days

3

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 6Sep 14Sep 22Sep 30Oct 8Oct 16Oct 24Nov 1

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Sun, Sep 6, 2026	+0	+0	0
Mon, Sep 7, 2026	+0	+0	0
Tue, Sep 8, 2026	+1	+1	0
Wed, Sep 9, 2026	+2	+0	0
Thu, Sep 10, 2026	+3	+0	0
Fri, Sep 11, 2026	+2	+0	0
Sat, Sep 12, 2026	+2	+0	0
Sun, Sep 13, 2026	+1	+0	0
Mon, Sep 14, 2026	+3	+0	1
Tue, Sep 15, 2026	+2	+0	1
Wed, Sep 16, 2026	+3	+1	0
Thu, Sep 17, 2026	+1	+0	0
Fri, Sep 18, 2026	+2	+2	0
Sat, Sep 19, 2026	+2	+0	0
Sun, Sep 20, 2026	+2	+0	0
Mon, Sep 21, 2026	+3	+0	0
Tue, Sep 22, 2026	+3	+0	0
Wed, Sep 23, 2026	+1	+0	0
Thu, Sep 24, 2026	+1	+0	3
Fri, Sep 25, 2026	+1	+0	0
Sat, Sep 26, 2026	+2	+0	0
Sun, Sep 27, 2026	+0	+0	0
Mon, Sep 28, 2026	+1	+0	0
Tue, Sep 29, 2026	+2	+1	0
Wed, Sep 30, 2026	+0	+1	0
Thu, Oct 1, 2026	+0	+0	0
Fri, Oct 2, 2026	+2	+0	0
Sat, Oct 3, 2026	+2	+0	0
Sun, Oct 4, 2026	+0	+0	0
Mon, Oct 5, 2026	+2	+0	0
Tue, Oct 6, 2026	+2	+0	0
Wed, Oct 7, 2026	+0	+0	0
Thu, Oct 8, 2026	+3	+1	0
Fri, Oct 9, 2026	+0	+1	0
Sat, Oct 10, 2026	+0	+0	0
Sun, Oct 11, 2026	+0	+0	0
Mon, Oct 12, 2026	+3	+0	0
Tue, Oct 13, 2026	+1	+0	0
Wed, Oct 14, 2026	+1	+1	0
Thu, Oct 15, 2026	+0	+0	0
Fri, Oct 16, 2026	+1	+0	0
Sat, Oct 17, 2026	+1	+0	0
Sun, Oct 18, 2026	+1	+1	0
Mon, Oct 19, 2026	+1	+0	0
Tue, Oct 20, 2026	+1	+1	0
Wed, Oct 21, 2026	+4	+1	0
Thu, Oct 22, 2026	+0	+0	1
Fri, Oct 23, 2026	+1	+0	0
Sat, Oct 24, 2026	+4	+0	0
Sun, Oct 25, 2026	+0	+0	0
Mon, Oct 26, 2026	+3	+0	0
Tue, Oct 27, 2026	+2	+0	0
Wed, Oct 28, 2026	+0	+1	0
Thu, Oct 29, 2026	+1	+0	0
Fri, Oct 30, 2026	+3	+0	0
Sat, Oct 31, 2026	+2	+1	0
Sun, Nov 1, 2026	+2	+0	0
Mon, Nov 2, 2026	+1	+0	0
Tue, Nov 3, 2026	+0	+0	0
Wed, Nov 4, 2026	+0	+0	0
Thu, Nov 5, 2026	+1	+0	0
Total	+85	+14	6

#1 on the list
Rank that day
Not trending

Mentions and achievements

Where people are talking about jmaczan/tiny-vllm, and every badge it has earned

Nov 11 post
- ok so you can now place an ad in tiny-vllm repo (1.2k GitHub stars, 100 forks) and get in front of thousands of llm inference devs (and support my ai research XD) four tiers: $2000/mo $500/mo $100/mo…
  Read full on X, posted by @jedmaczan
  @jedmaczan · x.com
4 months earlier
Jun 291 post
- AMD contributes their GPU support to tiny-vLLM
  Read full on Hacker News
  Hacker News
25 days earlier
Jun 41 post
- Tiny-vLLM: high-performance LLM inference in pure C++ and CUDA. No Python, no PyTorch. For edge deployment and agent pipelines where latency kills, the stack simplification alone is worth a serious…
  Read full on X, posted by @azarnoush
  @azarnoush · x.com
Jun 12 posts
- 12/ Las 4 herramientas de hoy: una te cambia la factura, otra entra en tu escritorio, dos te dan inference sin cloud. Si te sirve este filtro, cada semana llega al correo sin depender del algoritmo:…
  Read full on X, posted by @dorlando1997
  @dorlando1997 · x.com
- 2/ Openrsync — ISC rsync rewrite from the OpenBSD team, now in macOS 15. The attention spike followed regression reports tied to AI-generated patches in upstream Samba rsync
  Read full on X, posted by @prodimpossible
  @prodimpossible · x.com
May 311 post
- Tiny-vLLM got an attention on HackerNews yesterday. People wrote that they liked the lesson style of README. Any ideas what to do with that? I never had such a "semi-popular" project before🤷
  Read full on X, posted by @jedmaczan
  @jedmaczan · x.com
May 303 posts
- If you want to understand vLLM internals, reading C++ and CUDA is faster than Python. Tiny-vLLM is a from-scratch inference engine in C++/CUDA, 176 HN points. Good learning artifact if you run your…
  Read full on X, posted by @theaibenchai
  @theaibenchai · x.com
- Author frames it as a learning tool or teaching resource — meant to be picked up, mistakes included, rather than a production drop-in for vLLM.
  Read full on X, posted by @38twelveDaily
  @38twelveDaily · x.com
- jmaczan/tiny-vllm: Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
  Read full on X, posted by @0x440x46
  @0x440x46 · x.com
May 291 post
- Shift will clean homes for free to train future robots (
  Read full on X, posted by @betterhn20
  @betterhn20 · x.com