Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as a specialized runtime that prioritizes accelerated token generation and efficient hardware utilization for text generation tasks. The project distinguishes itself through a comprehensive suite of optimization techniques, including a graph compilation engine that transforms neural network operations into pre-compiled execution plans. It also incorporates a tensor parallelism framework to distribute model weights across multiple hardware accelerators, effectively reducing memor
The main features of zhangxj199/tinyllava-video are: Small Multimodal Models, Small Vision Models.
Open-source alternatives to zhangxj199/tinyllava-video include: ai-study-han/zero-qwen-vl. coobiw/mpp-llava. emericen/tiny-qwen. geeeekexplorer/nano-vllm — Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as… huggingface/nanovlm — nanoVLM is a training framework and toolkit for small vision-language models. It provides a PyTorch-based environment… jingyaogong/minimind-o.