Search Results for "decoding"
Sort By:
Showing 450 open source projects for "decoding"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
h265web.js
A HEVC/H.265 Web Player
...The project includes components for parsing H.265 bitstreams into NAL units and decoding them into raw YUV frames that can then be rendered onto a canvas or processed further. Its architecture separates parsing, decoding, and rendering, giving developers fine-grained control over how video data is handled and displayed. The system is designed to work with streaming data, allowing incremental feeding of video chunks and real-time decoding, which is useful for surveillance, streaming platforms, and custom media pipelines. -
2
Strata
Qwen3.8-Flash-Next on any consumer hardware
...It is designed to make a very large mixture-of-experts model practical with one NVIDIA GPU, system RAM, and local storage instead of server-class hardware. Frequently used experts remain on the GPU while other model components are shared across RAM, CPU, and SSD resources. Speculative decoding uses a smaller helper component to propose tokens that the main model verifies in batches. Long prompts are processed in large blocks to improve ingestion speed. Strata provides a local chat interface and exposes OpenAI- and Anthropic-compatible APIs for other applications. Optional image input and several quantized model sizes allow users to balance memory use, speed, and quality. -
3
JavaScript Cookie
A simple, lightweight JavaScript API for handling browser cookies
...Please note that the default encoding/decoding strategy is meant to be interoperable only between cookies that are read/written by js-cookie. To override the default encoding/decoding strategy you need to use a converter. -
4
DeepSpec
A full-stack codebase for training and evaluating speculative decoding
...The evaluation pipeline measures speculative decoding performance across benchmark tasks such as math, coding, instruction-following, and chat-style datasets. Overall, it is useful for researchers and engineers studying faster language model inference through speculative decoding methods. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
WhoDB
A lightweight next-gen data explorer
WhoDB is a lightweight audit logging extension for PostgreSQL that helps track who accessed what data and when. It uses logical decoding and hooks into PostgreSQL internals to log query metadata, user identities, and timestamps in a separate audit schema. WhoDB is useful for compliance, security monitoring, and debugging in multi-user environments. -
6
mpv
Command line video player
...While mpv strives for minimalism and provides no real GUI, it has a small controller on top of the video for basic control. mpv has an OpenGL, Vulkan, and D3D11 based video output that is capable of many features loved by videophiles, such as video scaling with popular high quality algorithms, color management, frame timing, interpolation, HDR, and more. mpv can leverage most hardware decoding APIs on all platforms. Hardware decoding can be enabled at runtime on demand. A straightforward C API was designed from the ground up to make mpv usable as a library and facilitate easy integration into other applications. mpv is under active development, focusing on code refactoring and cleanups. -
7
DFlash
Block Diffusion for Ultra-Fast Speculative Decoding
DFlash is an open-source framework for ultra-fast speculative decoding using a lightweight block diffusion model to draft text in parallel with a target large language model, dramatically improving inference speed without sacrificing generation quality. It acts as a “drafter” that proposes likely continuations which the main model then verifies, enabling significant throughput gains compared to traditional autoregressive decoding methods that generate token by token. -
8
io-ts
Runtime type system for IO decoding/encoding
Runtime type system for IO decoding/encoding -
9
jsonista
Clojure library for fast JSON encoding and decoding
Clojure library for fast JSON encoding and decoding. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
libavif
Library for encoding and decoding .avif files
libavif is a portable, open-source C library that implements encoding and decoding for the AVIF (AV1 Image File Format), offering a robust, production-ready way to work with AVIF images across platforms. It supports all AV1-supported YUV formats and bit-depths, including alpha (transparency), and includes command-line tools (avifenc and avifdec) to easily convert to/from AVIF from common image formats like JPEG, PNG, or Y4M. -
11
PXPlay (PSPlay)
A repo to host the official builds of the PXPlay application
...It allows users to connect to their PlayStation 4 or PlayStation 5 consoles and play games through a network connection. The software supports USB and Bluetooth controllers, along with basic keyboard input. Users can adjust streaming bitrate, display scaling, and video decoding settings to optimize performance. It also provides multiple console registration for switching between different PlayStation systems. Advanced rendering options include hardware-accelerated decoding and Vulkan-based image enhancement. Available for Windows, macOS, Linux, Android, iOS, and Apple TV, PXPlay offers a customizable alternative for remote console gaming. -
12
R-KV
Redundancy-aware KV Cache Compression for Reasoning Models
R-KV is an open-source research project that focuses on improving the efficiency of large language model inference through key-value cache compression techniques. Modern transformer models rely heavily on KV caches during autoregressive decoding, which store intermediate attention states to accelerate generation. However, these caches can consume large amounts of memory, especially in reasoning-oriented models with long context windows. R-KV introduces a method for compressing the KV cache during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. ... -
13
SatDump
A generic satellite data processing software
SatDump is a free, open-source satellite data processing application designed for receiving, decoding, and analyzing transmissions from numerous satellites. It supports real-time signal reception through compatible software-defined radio devices and offline processing of recorded data. The application provides specialized decoding pipelines for different satellite systems, modulation formats, and data products. Users can transform received signals into imagery, telemetry, and other interpretable outputs. ... -
14
mpv.net
mpv.net is a modern media player for Windows that works just like mpv
...Video output that is capable of many features loved by videophiles, such as video scaling with popular high-quality algorithms, color management, frame timing, interpolation, HDR, and more. Leverages the FFmpeg hwaccel APIs to support DXVA2 video decoding acceleration. mpv.net is based on libmpv which offers a straightforward C API that was designed from the ground up to make mpv usable as a library and facilitate easy integration into other applications. mpv is like VLC not based on DirectShow or Media Foundation. -
15
Jansson
C library for encoding, decoding and manipulating JSON data
Jansson is a C library for encoding, decoding and manipulating JSON data. -
16
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
FlashMLA is a high-performance decoding kernel library designed especially for Multi-Head Latent Attention (MLA) workloads, targeting NVIDIA Hopper GPU architectures. It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. -
17
OAuth2 (Client)
An Elixir OAuth 2.0 Client Library
This library can be configured to handle encoding and decoding requests and responses automatically based on the accept and/or content-type headers. An Elixir OAuth 2.0 Client Library. This library can be configured to handle encoding and decoding requests and responses automatically based on the accept and/or content-type headers. The http client library used is tesla, the default adapter is Httpc, since it comes out of the box with every Erlang instance but you can easily change it to something better. -
18
he
A robust HTML entity encoder/decoder written in JavaScript
...It emphasizes correctness, security (avoiding common pitfalls when decoding entities), and broad compatibility (browser, Node.js). The API is straightforward, documented, and used across modules that require reliable entity handling (e.g., for HTML sanitization or templating). Its longevity and adoption make it a go-to library for developers needing entity handling beyond minimal ad-hoc hacks. -
19
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
Model Optimizer is a unified library that provides state-of-the-art techniques for compressing and optimizing deep learning models to improve inference efficiency and deployment performance. It brings together multiple optimization strategies such as quantization, pruning, distillation, and speculative decoding into a single cohesive framework. The library is designed to reduce model size and computational requirements while maintaining accuracy, making it particularly valuable for deploying large models in production environments. It supports a wide range of model types, including large language models, diffusion models, and vision-language models, and integrates with deployment frameworks such as TensorRT and vLLM. ... -
20
io-ts
Runtime type system for IO decoding/encoding
io-ts is a TypeScript runtime type system for decoding, validating, and encoding data at application boundaries. It solves a common TypeScript limitation: static types disappear at runtime, but external inputs still need to be checked safely. The library lets developers define codecs that represent both runtime validation logic and static TypeScript types. This approach is especially useful for APIs, configuration files, JSON payloads, database results, and any data that enters a program from an unknown source. io-ts integrates closely with functional programming patterns and the fp-ts ecosystem. ... -
21
Jessibuca
Jessibuca is an open source pure H5 live streaming player
Jessibuca is an open-source HTML5 live streaming player that runs entirely in the browser using WebAssembly to decode audio and video streams without requiring plugins. It compiles native decoding libraries into JavaScript, enabling high-performance playback across desktop and mobile devices. The player supports modern streaming protocols and codecs, allowing it to handle real-time video feeds with low latency and stable rendering. Its architecture is modular, separating decoding, demuxing, and rendering to optimize performance and scalability. ... -
22
Omnilingual ASR
Omnilingual ASR Open-Source Multilingual SpeechRecognition
...It focuses on leveraging self-supervised audio pretraining and scalable fine-tuning so low-resource languages can benefit from high-resource data. The project provides data preparation pipelines, training scripts, decoding utilities, and evaluation tools so researchers can reproduce results and extend to new language sets. It emphasizes modularity: acoustic modeling, language modeling, tokenization, and decoding are separable pieces you can swap or ablate. The repo is aimed at pushing practical multilingual ASR—robust to accents, code-switching, and domain shifts—rather than language-by-language systems. ... -
23
Clypra
Hardware-accelerated video editor built on Rust, Tauri v2 & React 19
...Its multitrack timeline supports frame-accurate trimming, layered arrangements, and undo and redo controls. A native Rust engine combines FFmpeg processing with GPU acceleration for video decoding and rendering. Audio tools include waveform visualization, synchronized audio and video playback, and individual clip volume controls. Users can add styled text, animated overlays, and filters while previewing their compositions. The editor supports common video, audio, and image formats, with H.264 and ProRes export options. -
24
Zydis
Fast and lightweight x86/x86-64 disassembler and code generation lib
Zydis is a fast and lightweight disassembler library designed for decoding x86 and x86-64 machine code into human-readable assembly instructions. It focuses on performance and accuracy, making it suitable for applications such as reverse engineering, debugging, and binary analysis. The library provides detailed information about decoded instructions, including operands, prefixes, and instruction lengths, enabling deep inspection of executable code. -
25
The Bitdefender disassembler
bddisasm is a fast, lightweight, x86/x64 instruction decoder
The Bitdefender disassembler is a highly optimized, lightweight x86/x64 instruction decoder designed for security, reverse engineering, and low-level systems analysis. It focuses on decoding machine instructions with high precision while providing detailed metadata about each instruction, including operands, access modes, CPU flags, and feature requirements. Unlike many disassemblers, bddisasm is built with zero dynamic memory allocation and no external dependencies, making it extremely portable and suitable for constrained environments such as kernels, hypervisors, and embedded systems. ...
