Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…

State-of-the-art TTS model under 25MB 😻

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

A huge collection of Rofi based custom Applets, Launchers & Powermenus.

Core, junction, and VRAM temps for GDDR6, GDDR6X, GDDR7 NVIDIA GPUs in Linux

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

A self-managed ArgoCD homelab kubernetes cluster using Talos

A guide on using NVidia GPUs for transcoding or AI in Kubernetes

Tile primitives for speedy kernels

Official repo for Memtest86+

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Efficient Triton Kernels for LLM Training

curl-impersonate: A special build of curl that can impersonate Chrome & Firefox

Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser tls/ja3/http2 fingerprints.

A user-friendly, lightweight TUI for disk imaging

SGLang is a high-performance serving framework for large language models and multimodal models.

View model summaries in PyTorch!

Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.

NVIDIA GPUDirect Storage Driver

OCR, layout analysis, reading order, table recognition in 90+ languages

Lightweight Kubernetes

A python client + documentation for the Colmi R02 smart ring

FOSS Image background remover with 10 open source rmbg models

This is a background removing tool powered by InSPyReNet (ACCV 2022)

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022)