Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
Repository Index
111,821 visible repositories in the index
169–192 of 315 · Most stars
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
Inference Microsoft Florence2 VLM
Official PyTorch inference for Breeze TTS 2
Python package for compiling and analyzing quantum algorithms to simulate electronic structures.
- quantum-computing
- quantum-chemistry
- quantum-algorithms
- quantum-programming-language
Causal Discovery in Python. Learning causality from data.
- causal
- causal-discovery
- causal-inference
- causality
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
Reference implementations of MLPerf® inference benchmarks
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Add bisenetv2. My implementation of BiSeNet
- bisenet
- cityscapes
- pytorch
- cocostuff
General code to convert a trained keras model into an inference tensorflow model
Awesome resources on normalizing flows.
- normalizing-flows
- bayesian-neural-networks
- variational-inference
- density-estimation
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"
- nlp
- python
- machine-learning
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
- convolutional-neural-networks
- bayesian-network
- bayesian-convnets
- bayes-by-backprop
The repository host gives no description.
V100 / SM70-focused vLLM engineering fork for modern LLM inference.
Take your video conference from within the matrix.
Yolov5 deepsort inference,使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中
- yolov5-deepsort-inference
- yolov5
- deepsort
- object-detection
PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
- diffusion-models
- inference-acceleration
- video-generation
- cogvideox