hr98w/jev-visual
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
About the project
An educational project for running vision-language model inference on Apple Silicon via MLX: answers multiple questions about one image by choosing options or scoring levels, without autoregressive generation.
Useful for
- Run the local server and classify an image by answer options in the browser
- Compare independent vs shared-prefix candidate scoring speed with the benchmark
- Study the prefill, KV-cache reuse and logit scoring stages in the code
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 46 stars so far today, about 61 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 100 stars.
- Top new repositories this week: #118.
- About 11 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 100
- Stars in a day
- 61
- Forks
- 11
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 17, 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, 2026Top new repositories this week: #118
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/hr98w/jev-visual)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.
-
6.6
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.
-
4.9
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.