Repo

open-model-engine

@ayenioluwatosinolawaleby Ayeni Oluwatosin Olawale · Vertinab

0

GPU-first inference benchmarking engine for self-hosted open models (vLLM, SGLang, TensorRT-LLM). Deep CUDA profiling via Nsight Systems, quantization, speculative decoding, multi-GPU scaling.

Built withPython

See what other members are building and what each project is looking for.