标签：inference
查找带有 inference 标签的 Jev GitHub 项目，筛选、排序并查看原始仓库。
- 10laya-mlxNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
mizorewww/laya-mlx · Python
6,878558apple-silicondecision-modelinferencelayalocal-aimachine-learningmlxmodernbert - 133jevfireJEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
kikoncuo/jevfire · JavaScript
758javascriptcudagame-aiinference - 199levJolt implementation of Laya non-autoregressive System 1 decision engine
jlt-commons/lev · Clojure
281bertblaschez-schemeclojureffiinferencejolt - 233fastjevSDK-first, independently maintained SemIf fork for fast, self-hosted semantic decisions.
chengyongru/fastjev · Python
210inferencellmpythonsdksemantic-decisions - 343typed-lmSingle-forward-pass semantic routing in Rust: turn dense LLMs (Llama, Qwen, Mistral, Gemma) into a typed decision API with LoRA/QLoRA training and FP8/FP4 quantization, built on Candle.
neurono-ml/typed-lm · Rust
100actix-webcandleclassificationhuggingfaceinferencellmlora - 500jevtppJev-like decisions. Strong C++ types.
wiatrM/jevtpp · C++
51c++cpp20ggmlinferencelayamachine-learningobservability - 732jev-bridgeJev-style /v1/systemone API in front of any OpenAI-compatible LLM server (one-token logprob scoring, MIT)
TOSUKUi/jev-bridge · Python
21classificationinferencellmlogprobsopenai-compatiblesglang - 1085jevlinZig SDK for TypeSafe AI's Jev decision API. Typed classification, scoring and yes/no probabilities with bounded buffers, retries and deadlines.
copyleftdev/jevlin · Zig
11api-clientclassificationdecision-apifault-injectioninferencesdk
第 1–8 条，共 8 条