标签：Transformers

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia (CUDA), AMD (ROCm), Intel GPU (XPU), Huawei Ascent (NPU), and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

Neural Network Compression Framework for enhanced OpenVINO™ inference

About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

Official repository of my book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face"

Halo is an open-source framework built by White Circle for training large language and multimodal models

Llama 3+ inference in pure Java

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

Pure Rust Inference Engine

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.

A flexible, adaptive classification system for dynamic text classification

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

The Official Repo for "Quick Start Guide to Large Language Models"

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

Live-bending a foundation model’s output at neural network level.

Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.