Search

⚡ Automatically decrypt encryptions without knowing the key or cipher, decode encodings, and crack hashes ⚡

Dart library to encode and decode various archive and compression formats, such as Zip, Tar, GZip, ZLib, and BZip2.

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.

c common functions library extracted from my open source project FastDFS. this library is very simple and stable. functions including: string, logger, chain, hash, socket, ini file reader, base64 encode / decode, url encode / decode, fast timer, skiplist, object pool etc. detail info please see the c header files.

encode & decode HTML & XML entities with ease & speed

Program to decode radio transmissions from devices on the ISM bands (and other frequencies)

Software defined LaserDisc decoder

WavPack encode/decode library, command-line programs, and several plugins

Minimal audio decoders layer

Teletext streaming. Generates a T42 teletext stream from teletext pages. This can be used with inserter hardware or a Raspberry Pi to generate a video signal that teletext TVs can decode and display. It can also be used with vbit-iv to generate in-vision teletext on a Linux PC or Raspberry Pi.

A simple to use Java JWT Library. Verify, Sign, Encode, Decode all day.

A library to help you decode JWTs for Android

decode, inspect, edit, and encode png images in pure swift

decode, inspect, edit, and encode jpeg images in pure swift

Decode CINRAD (China New Generation Weather Radar) data and visualize.

Apple SMC CLI — decode temperature, fans, battery, power, voltage and current on macOS

Kubernetes CLI plugin to decode Kubernetes secrets

Describe binary structures with full TypeScript support. Encode and decode into pure JavaScript objects.

Lossless compression C library built for ultra-fast decode. Faster than LZ4 (+35% to 105%+; best on ARM64), at a better ratio. Official Rust, Python, Node.js, Go and WASM bindings. Write-once/read-many, with optional seekable archives for O(1) random access.

Media player engine for iOS, tvOS, macOS and visionOS. FFmpeg demux, VideoToolbox / dav1d / libavcodec decode (HEVC, H.264, AV1, VP9, MPEG-2, VC-1), live TV with DVR timeshift and hardware deinterlace, Dolby Atmos passthrough, HDR10 / HDR10+ / Dolby Vision / HLG, text + bitmap + teletext subtitles, plus a lean audio-only path. You ship the UI.

W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.

2.24x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://discord.gg/VFqVVySdMS )

Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.