Kh4L/deepseek-harness
DeepSeek Harness: Everything is a Plugin.
Repositories
Kh4L/pi-mono
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
Kh4L/relbench
RelBench: Relational Deep Learning Benchmark
Kh4L/raft
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
Kh4L/NemoRL
Scalable toolkit for efficient model reinforcement
Kh4L/recipes
Common recipes to run vLLM
Kh4L/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Kh4L/NemoGym
Build RL environments for LLM training
Kh4L/flashinfer
FlashInfer: Kernel Library for LLM Serving
Kh4L/NemoClaw
Run OpenClaw more securely inside NVIDIA OpenShell with managed inference
Kh4L/OpenShell
OpenShell is the safe, private runtime for autonomous AI agents.
Kh4L/claw-code
The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex.
Kh4L/autoresearch
AI agents running research on single-GPU nanochat training automatically
Kh4L/sglang
SGLang is a fast serving framework for large language models and vision language models.
Kh4L/jepa_graph
Graph-JEPA: GNN+LLM with JEPA pretraining
Kh4L/flash-attention
Fast and memory-efficient exact attention
Kh4L/torchcodec
PyTorch media decoding and encoding
Kh4L/kg-gen
Knowledge Graph Generation from Any Text
Kh4L/faiss
A library for efficient similarity search and clustering of dense vectors.
Kh4L/pyg-lib
Low-Level Graph Neural Network Operators for PyG
Kh4L/transformers
👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)
Kh4L/open-r1
Fully open reproduction of DeepSeek-R1
Kh4L/pytorch_geometric
Graph Neural Network Library for PyTorch
Kh4L/gfm-rag
Graph Foundation Model for Retrieval Augmented Generation
Kh4L/rnn
Custom C++ vanilla RNN implementation with Eigen
Kh4L/SubgraphRAG
Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
Kh4L/onnx
Open standard for machine learning interoperability
Kh4L/gluon-nlp
NLP made easy
Kh4L/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
Kh4L/stable_diffusion_playground
Playing around with stable diffusion. Generated images are reproducible because I save the metadata and latent information. You can generate and then later interpolate between the images of your choice.