-
Model-Optimizer Public
Forked from NVIDIA/Model-OptimizerA unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
-
DeepSpec Public
Forked from deepseek-ai/DeepSpecDeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
-
flash-attention Public
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
-
mlx Public
Forked from ml-explore/mlxMLX: An array framework for Apple silicon
-
next.js Public
Forked from vercel/next.jsThe React Framework
-
node Public
Forked from nodejs/nodeNode.js JavaScript runtime ✨🐢🚀✨
-
spark Public
Forked from apache/sparkApache Spark - A unified analytics engine for large-scale data processing
-
mteb Public
Forked from embeddings-benchmark/mtebMTEB: Massive Text Embedding Benchmark
-
newton Public
Forked from newton-physics/newtonAn open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
-
robots Public
Forked from strands-labs/robotsControl robots and physical hardware with natural language through Strands Agents.
-
bionemo-framework Public
Forked from NVIDIA-BioNeMo/bionemo-recipesBioNeMo Framework: For building and adapting AI models in drug discovery at scale
-
cudnn-frontend Public
Forked from NVIDIA/cudnn-frontendcuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
-
omnigent Public
Forked from omnigent-ai/omnigentA meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in che…
-
opensquilla Public
Forked from opensquilla/opensquillaOpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
-
linguist Public
Forked from github-linguist/linguistLanguage Savant. If your repository's language is being reported incorrectly, send us a pull request!
-
mini-swe-agent Public
Forked from SWE-agent/mini-swe-agentThe 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
-
SWE-agent Public
Forked from SWE-agent/SWE-agentSWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
-
unsloth Public
Forked from unslothai/unslothUnsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
OpenEnv Public
Forked from huggingface/OpenEnvAn interface library for RL post training with environments.
-
llama.cpp Public
Forked from ggml-org/llama.cppLLM inference in C/C++
-
optuna Public
Forked from optuna/optunaA hyperparameter optimization framework
-
bigset Public
Forked from tinyfish-io/bigsetWhat if you had all the data in the world?
-
Megatron-Bridge Public
Forked from NVIDIA-NeMo/Megatron-BridgeTraining library for Megatron-based models with bidirectional Hugging Face conversion capability
-
Megatron-LM Public
Forked from NVIDIA/Megatron-LMOngoing research training transformer models at scale
-
OpenShell Public
Forked from NVIDIA/OpenShellOpenShell is the safe, private runtime for autonomous AI agents.
-
NemoClaw Public
Forked from NVIDIA/NemoClawRun agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference
-
alpasim Public
Forked from NVlabs/alpasimAlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies
-
keycloak Public
Forked from keycloak/keycloakOpen Source Identity and Access Management For Modern Applications and Services
-
sia Public
Forked from hexo-ai/siaSIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.
-
Eagle Public
Forked from NVlabs/EagleEagle: Frontier Vision-Language Models with Data-Centric Strategies