Neroued/ninfer
High-performance single-GPU inference for selected model checkpoints and GPUs.
About the project
NInfer is a from-scratch C++/CUDA inference engine for Qwen3.5 Dense and MoE models on a single NVIDIA RTX 5090. It serves text, image, and video prompts via a local CLI or OpenAI-/Anthropic-compatible HTTP APIs.
Useful for
- Start a local Qwen3.8-27B inference server with two concurrent requests and a 240,000-token context.
- Send an OpenAI-compatible request to the local model via curl for text generation.
- Run a one-shot CLI request with an image or video using the --vision flag.
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 38 stars so far today, about 47 expected by the end of the day.
- Over the last two days the pace is 1.5× that of the previous week and a half.
- GitHub Trending C++ today: #3, +82 stars.
- About 7 forks a day — people are taking the code.
- Recent forks include notable developers: @JarodMica (681 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 2,080
- Stars in a day
- 47
- Forks
- 381
- Issues and pull requests
- 280
- Watchers
- 18
- Language
- C++
- License
- Apache-2.0
- Created
- June 26, 2026
- Last push
- September 18, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 18, 2026GitHub Trending C++ today: #3, +82 stars
- September 17, 2026GitHub Trending C++ today: #3, +72 stars
- September 16, 2026GitHub Trending C++ today: #2, +112 stars
- September 15, 2026GitHub Trending C++ today: #2, +136 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Neroued/ninfer)Similar projects
-
8.6
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
7.1
vinnylarouge/jevlike
A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection…
-
6.9
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.4
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.
-
5.0
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.