FareedKhan-dev/kimi-k3-in-c
kimi-k3-in-c is a portable C99 inference engine designed to run the Kimi K3 2.78-trillion-parameter LLM on a single CPU with minimal RAM, focusing on extreme memory efficiency without GPUs or exter...
Awesome Infra for AI › Inference Optimization
msnh2012/Msnhnet
Msnhnet is a concise C++ inference framework designed for efficient deployment of PyTorch-trained deep learning models. Inspired by Darknet, it focuses on providing a fast and flexible solution for model inference on diverse hardware platforms including Windows, Linux, and Mac OS, with specific optimizations for ARM-based CPUs (like Raspberry Pi and Jetson NX) and various GPUs (NVIDIA CUDA/cuDNN with FP16 support). The framework features support for a wide array of popular models such as YOLO (v3, v4, v5), UNet, MobileNetV2, and various ResNet and VGG variants, making it suitable for computer vision applications. It includes integrations for Keras and PyTorch models, a network viewer akin to Netron, and a C API for broader compatibility. Msnhnet aims to facilitate the transition of trained models into production environments, particularly for robot vision, by emphasizing performance, small footprints, and broad hardware compatibility, evidenced by its detailed performance benchmarks across different devices and networks.
https://github.com/msnh2012/Msnhnet
Also in Inference Optimization
zilliztech/GPTCache
GPTCache is a library that creates a semantic cache for LLM queries, significantly reducing API costs and improving response times by storing and reusing previous LLM responses.
vllm-project/vllm-ascend
vLLM Ascend is a community-maintained hardware plugin for seamlessly running vLLM and various large language models on Ascend NPUs, optimizing inference performance.
youssofal/MTPLX
MTPLX is a macOS-native inference engine for Apple Silicon that leverages multi-token prediction (MTP) for accelerated local LLM serving, offering significant speed improvements.
open-compress/claw-compactor
Claw Compactor is an LLM token compression engine that uses a 14-stage Fusion Pipeline for content-aware, reversible compression to reduce LLM inference costs and optimize context windows.
siliconflow/onediff
OneDiff is an acceleration library for diffusion models, providing out-of-the-box performance optimizations for popular UIs and libraries like Hugging Face Diffusers and ComfyUI.
ovg-project/kvcached
kvcached is a KV cache library that introduces virtual memory abstraction for LLM serving on shared GPUs, enabling elastic and demand-driven KV cache allocation for improved GPU utilization under d...
nobodywho-ooo/nobodywho
NobodyWho is an efficient, on-device inference engine that enables local execution of LLMs and SLMs across various platforms without requiring API keys.