Stars
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
The Forge Cross-Platform Framework PC Windows, Steamdeck (native), Ray Tracing, macOS / iOS, Android, XBOX, PS4, PS5, Switch, Quest 2
AI agents running research on single-GPU nanochat training automatically
Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory …
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Boosting 4-bit inference kernels with 2:4 Sparsity
PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure
Continued development of the popular brainworkshop game
A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation
dommrogers / ModComponent
Forked from ds5678/ModComponentInfrastructure library for The Long Dark, allowing to add new items.
A mod for The Long Dark that adds tools for outdoors adventures.
🍱 Semantically create chunks from large document for passing to LLM workflows
Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray
🍼 Plugin driven WYSIWYG markdown editor framework.
Unlock full RTX 5080 performance in PyTorch! PyTorch does not support RTX 5080 (sm_120) natively, so I built custom CUDA 12.8 drivers and PyTorch binaries to make it work. This repo contains build …
A framework for few-shot evaluation of language models.
A collection of benchmarks and datasets for evaluating LLM.
Application designed to optimize, customize and enhance your Windows experience.
Fine-Tuning Llama 3.1 70B on DGX Spark
A library for making RepE control vectors
Genertaes control vectors for use with llama.cpp in GGUF format.