Strot
Compile an LLM's intent once, run decisions locally. STROT (arXiv:2505.01636): compile-time LLM code synthesis with deterministic, self-routing NLU runtimes. PyPI: strot-ai.
오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
LLM
github.coma Rust Crate/CLI for CPU Inference of LLMs (LLaMA, GPT-NeoX, etc.)
Can your GPU run this LLM?
github.comCalculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Tiny-vLLM
github.comhigh performance LLM inference engine in C++ and CUDA
Nibble
github.comGenerating LLVM IR without malloc or external dependencies
Edge full-stack LLM platform. Written in Rust