lkk

AI agents running research on single-GPU nanochat training automatically

SOTA Weight-only Quantization Algorithm for LLMs

🔐 AI decoding Trump's posts × stock market | AI 解碼川普推文 × 美股 | AIでトランプ投稿×株式市場を解読 — 31.5M models, 61.3% hit rate, open source

🙌 OpenHands: AI-Driven Development

Training library for Megatron-based models with bi-directional Hugging Face conversion capability

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

The absolute trainer to light up AI agents.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Community maintained hardware plugin for vLLM on Intel Gaudi

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Autonomous GPU Kernel Generation via Deep Agents

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Development repository for the Triton language and compiler

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

OpenAI Triton backend for Intel® GPUs

Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.

A high-throughput and memory-efficient inference and serving engine for LLMs

adversarial rounding

Reference implementations of MLPerf® inference benchmarks

A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.

Samples for Intel® oneAPI Toolkits

No description provided.

A safetensors extension to efficiently store sparse quantized tensors on disk

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Sky-T1: Train your own O1 preview model on Intel Gaudi

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

PyTorch emulation library for Microscaling (MX)-compatible data formats