JEV-CPU

What it is

Semantic ifs from open models — on a laptop CPU, no GPU.

The homepage listed on the repository, leesk212.github.io, puts it like this: A technical report on JEV-CPU: running SemIf-style semantic-if decisions on a CPU by reading option logits from a small open model. English / Korean.

What the README says it does

• direct.py / shared.py follow device = next(model.parameters()).device
• torch.cuda.synchronize is called only when device.type == "cuda" (a no-op on CPU)
• option-logit slot extraction and softmax are pure math
• Runtime-defined: criteria and option descriptions arrive with the request.
• Decision-native: one forward pass reads declared option logits; no answer token is sampled.

From the project’s README.

Where the decision sits

JEV-CPU runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.

Models it references: JEV-CPU, jev.

How active it is

Created 2026-09-19, last pushed 2026-09-19, 18 stars and 4 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.