rockbenben/subtitle-translator 1,177 +2 today
RhythmicWave/NovelForge 1,255
NovelForge replaced its DAG editor with code, and ships a Windows-only start script
RefoundAI/lenny-skills 1,434
lenny-skills counts 86 skills in its description and 76 in its readme
PrunaAI/pruna 1,326 +1 today
Pruna's own table says the techniques that shrink a model cost quality
proxysoul/Empryo 1,451 +1 today
Empryo is source-available, and the public repository is only the core
PRIME-RL/TTRL 1,129
TTRL supervises a model with majority voting and then beats majority voting
ovg-project/kvcached 1,961 +28 today
kvcached reserves GPU address space before the KV cache exists
openvinotoolkit/nncf 1,211
NNCF's usage snippets all stop mid-statement, and its PyTorch floor has no classifier
nvk/llm-wiki 1,458 +6 today
llm-wiki's last five releases moved provider automation out of the public repository
NVIDIA-NeMo/Gym 1,269
NeMo Gym: A Server-Based Runtime for Stateful Agent Evaluation and RL Rollouts
NVIDIA/kvpress 1,237
kvpress: A Test Bench for KV Cache Compression Methods
NovaSearch-Team/RAG-Retrieval 1,136
RAG-Retrieval: One Codebase for Embedding, ColBERT and Reranker Fine-Tuning
nobodywho-ooo/nobodywho 1,643 +5 today
NobodyWho: a llama.cpp wrapper that ships the same chat API to Kotlin, Swift, Flutter, React Native, Expo, Python and Godot
ngxson/wllama 1,351 +1 today
wllama: llama.cpp Compiled to WebAssembly for In-Browser Inference
mrwadams/stride-gpt 1,145
STRIDE GPT: an LLM threat modeling front end with a CLI, a Streamlit app, and a diagram editor
mrwadams/attackgen 1,254