Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
Find trending repositories by name or description.
Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
A hardware-accelerated video editor built on Rust, Tauri v2, and React 19. Sub-10ms frame decoding, GPU-native rendering, and a frame-accurate timeline — all free and open source under MIT.
Browser-based ground station suite for celestial body, mission and satellite tracking, SDR reception, hardware control, and telemetry decoding
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.
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.
DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM kit, exact speculative decoding. Work in progress.
Fast Base64 encoding/decoding in Python
C library for encoding, decoding and manipulating JSON data
Encoding and decoding images in Rust
.NET library for encoding/decoding Base16, Base32, Base45, Base58, Base62, Base85, and Multibase.
radiosonde decoding
Encoding and decoding support for BSON in Rust
PNG decoding and encoding library in pure Rust
Clojure library for fast http api format negotiation, encoding and decoding.
A thin Swift wrapper around libwebp, offering both encoding and decoding APIs
fast raw decoding library
Clojure library for fast JSON encoding and decoding.
Pure Rust multimedia format demuxing, tag reading, and audio decoding library
python interface to the miniaudio audio playback, recording, decoding and conversion library
Scripts for decoding/encoding config.bin for ZTE routers
https://h265web.com 🔥 作者:常炎隆(Author: ChangYanlong):HEVC/H.265 网页直播/点播播放器 支持硬解! 支持H.265的HttpFLV/HLS/MP4/TS/FLV/M3U8/Websocket/WebRTC播放。 🔥 A HEVC/H.265 Web Player, Support hard-decoding! for LIVE/VOD stream. Support H.265 Codec with HttpFLV/HLS/MP4/TS/FLV/M3U8/Websocket/WebRTC.
Go library for detecting and decoding various content front matter formats
Image decoding for many popular formats for Simple Directmedia Layer.
Efficient, portable and lightweight library for Internet of Things payload decoding.
Automated decoding of encrypted text without knowing the key or ciphers used
A FIT SDK for decoding and encoding Garmin FIT files in Go supporting FIT Protocol V2.
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.