Search Results for "flash"
Sort By:
Showing 35 open source projects for "flash"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
1
Flash-MoE
Running a big model on a small laptop
Flash-MoE is a high-performance implementation of mixture-of-experts (MoE) architectures designed to optimize the efficiency and scalability of large AI models. It focuses on accelerating routing and computation by leveraging optimized kernels and memory management techniques, allowing models to dynamically select specialized sub-networks during inference. -
2
MiMo-V2-Flash
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation
...The repository typically serves as a launch point for running the model, understanding its intended use cases, and reproducing or extending its evaluation on reasoning and agent-style tasks. In short, MiMo-V2-Flash targets the “high-speed, high-competence” lane for modern LLM applications. -
3
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
Step 3.5 Flash is a cutting-edge, open-source large language model developed by StepFun-AI that pushes the frontier of efficient reasoning and “agentic” intelligence in a way that makes powerful AI accessible beyond proprietary black boxes. Unlike dense models that activate all their parameters for every token, Step 3.5 Flash uses a sparse Mixture-of-Experts (MoE) architecture that selectively engages only about 11 billion of its roughly 196 billion total parameters per token, delivering high-quality reasoning and interaction at far lower compute cost and latency than traditional large models. ... -
4
whisper.cpp
Port of OpenAI's Whisper model in C/C++
whisper.cpp is a lightweight, C/C++ reimplementation of OpenAI’s Whisper automatic speech recognition (ASR) model—designed for efficient, standalone transcription without external dependencies. The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples.... -
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.
-
5
ds4.c
DeepSeek 4 Flash local inference engine for Metal
ds4.c is a specialized local inference engine created by antirez for running DeepSeek V4 Flash models directly on Apple Silicon hardware using Metal acceleration. Unlike general-purpose inference runtimes, the project is intentionally optimized for a specific model family, enabling highly efficient execution and simplified architecture. The engine includes DS4-specific model loading, KV cache management, prompt rendering, and OpenAI-compatible server APIs for local deployment workflows. ... -
6
esp32-ai
Running a 28.9M parameter LLM on an $8 microcontroller
esp32-ai is an experimental language-model project that runs a 28.9-million-parameter model entirely on an ESP32-S3 microcontroller. The quantized model occupies about 14.9 MB and generates text without sending data to a server. Most parameters remain in flash through a Per-Layer Embeddings design, while active computation uses SRAM and PSRAM. This memory layout allows the device to retrieve only the embedding rows required for each token. The implementation reaches roughly 9.5 tokens per second and can display generated words on a connected screen. Trained on TinyStories, the model produces short, simple stories rather than answering questions, following instructions, or providing factual knowledge. ... -
7
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
Ring is a reasoning Mixture-of-Experts (MoE) large language model (LLM) developed by inclusionAI. It is built from or derived from Ling. Its design emphasizes reasoning, efficiency, and modular expert activation. In its “flash” variant (Ring-flash-2.0), it optimizes inference by activating only a subset of experts. It applies reinforcement learning/reasoning optimization techniques. Its architectures and training approaches are tuned to enable efficient and capable reasoning performance. Reasoning-optimized model with reinforcement learning enhancements. ... -
8
ElevenLabs Python
The official Python SDK for the ElevenLabs API
...The library wraps the HTTP API into a typed Python client, so you can perform text-to-speech, streaming, voice cloning, voice management, and agents-related operations with simple method calls. It exposes ElevenLabs’ main models such as Eleven Multilingual v2, Eleven Flash v2.5, and Eleven Turbo v2.5, each targeting different trade-offs between latency, cost, and quality. The SDK is designed for quick setup: after installing the package and setting an API key, you can generate speech in multiple languages and play or process the resulting audio bytes. It includes helper utilities (like play and stream) so you can either play audio locally or integrate it into your own playback or networking pipeline. -
9
LitGPT
20+ high-performance LLMs with recipes to pretrain, finetune at scale
LitGPT is a collection of over 20 high-performance large language models (LLMs) accompanied by recipes to pretrain, finetune, and deploy them at scale. It provides implementations without abstractions, making it beginner-friendly while offering advanced features like flash attention and support for various precision levels. LitGPT is designed to run efficiently across multiple GPUs or TPUs, catering to both small-scale and large-scale deployments. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
gemini-web2api
Convert Google Gemini web into OpenAI-compatible API
...It is designed to let OpenAI-style clients connect to Gemini-like models through routes such as chat completions, models, responses, and native Gemini-compatible endpoints. The project can run as a simple local server and uses a mostly single-file design with an optional dependency for streaming. It supports model aliases for Flash, Thinking, Pro-style routing, Auto, and Lite variants. The tool also includes optional API keys, function calling, SSE streaming, web search access, Docker deployment, and client examples for OpenAI SDK-style usage. It is useful for developers who want local experimentation with OpenAI-compatible tooling while routing requests through Gemini web behavior. -
11
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. It also supports advanced inference configurations such as Flash Attention v2 and multi-GPU inference setups for very large models. -
12
video-shotcraft
AI video skill for Claude Code & Codex
...Its Ink Press template delivers a complete 1080p product promo with ten shots, transitions, title cards, camera moves, and cinematic sound effects. Reusable components support page capture, 2.5D movement, captions, flash cuts, digit rolls, and branded asset replacement. It is intended for web and desktop promos, feature demonstrations, launches, and brand films. -
13
Tencent-Hunyuan-Large
Open-source large language model family from Tencent Hunyuan
Tencent-Hunyuan-Large is the flagship open-source large language model family from Tencent Hunyuan, offering both pre-trained and instruct (fine-tuned) variants. It is designed with long-context capabilities, quantization support, and high performance on benchmarks across general reasoning, mathematics, language understanding, and Chinese / multilingual tasks. It aims to provide competitive capability with efficient deployment and inference. FP8 quantization support to reduce memory usage... -
14
OpenBot
OpenBot leverages smartphones as brains for low-cost robots
OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones supports advanced robotics workloads such as person following and real-time autonomous navigation. Current robots are either expensive or make significant compromises on sensory richness, computational power, and communication capabilities. We propose to leverage smartphones to equip robots with... -
15
Gemini Next Chat
Deploy your private Gemini application for free with one click
Gemini Next Chat is an open-source web application that allows you to deploy your own private chat interface powered by Google’s Gemini models (e.g., Gemini 1.5, Gemini 2.0, etc.). It is built with Next.js/TypeScript and targets developers and hobbyists who want a self-hosted solution for interacting with advanced multimodal models (text, image, voice). It supports features like image recognition, voice-based conversation, plugins (web search, ArXiv search, weather, etc.), and client apps... -
16
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and... -
17
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
...The model excels at code generation, translation, summarization, debugging, and comment generation, and it supports over 100 programming languages. With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. Its backend powers the CodeGeeX IDE plugins for VS Code, JetBrains, and other editors, offering developers interactive AI assistance with features like infilling and cross-file completion. -
18
Insanely Fast Whisper
An opinionated CLI to transcribe Audio files w/ Whisper on-device
Insanely Fast Whisper is a high-performance command-line tool designed to dramatically accelerate speech-to-text transcription using OpenAI’s Whisper models on local hardware. It leverages modern optimizations such as batch processing, mixed precision, and advanced attention mechanisms like Flash Attention to significantly reduce inference time while maintaining high transcription accuracy. The project is built on top of the Transformers ecosystem and integrates with libraries such as Optimum to maximize GPU efficiency. It is specifically engineered for environments with CUDA-enabled GPUs or Apple Silicon devices, allowing users to process hours of audio in minutes or even seconds depending on hardware capabilities. ... -
19
PNotes is light-weight, flexible, skinnable manager of virtual notes on your desktop. It supports multiple languages, individual note's settings, transparency and scheduling. Absolutely portable as well - no traces in registry. PNotes.NET edition requires .NET framework 4 Client Profile
-
20
ViralMint
Open-source AI video pipeline, fully automated with MCP
...It transcribes top performers locally with Whisper, extracts the hook and structure with AI, then assembles original videos — AI-written scripts, AI voiceover (Gemini 3.1 Flash TTS, free Edge TTS, or a voice you cloned on-device), word-by-word animated captions and background music — or generates AI video clips with Sora 2 Pro, Veo 3.1, Seedance and Wan. Newer modes turn a prompt into motion-graphics animations (kinetic typography rendered from HTML) and turn any website URL into a polished promo video. -
21
...Powered by leading cloud and offline/local AI models including Google Gemini, OpenAI, xAI Grok, DeepL, Azure, and Ollama (Gemma, Qwen), it seamlessly translates 240+ languages with an intuitive, plug-and-play interface. Example: They speak German → you see Turkish They speak Turkish → you see German 🧠 AI Model Support Google Gemini: 2.5 Flash, 2.5 Pro OpenAI: GPT-4o, GPT-4 Turbo xAI: Grok Local/Offline (via Ollama Engine): Gemma, Qwen
-
22
goodsKill
Microservices-based flash sale system for high-concurrency testing
goodsKill is a simulated flash sale microservices project built with Spring Cloud 2023.x, Spring Boot 3.x, and Dubbo 3.x. It provides a unified API for testing high-concurrency seckill scenarios while demonstrating modern backend architecture patterns. goodsKill integrates key components such as Nacos for service discovery and configuration, Redis and MongoDB for data handling, and Kafka or RabbitMQ for messaging. -
23
Lightning Flash
Flash enables you to easily configure and run complex AI recipes
Your PyTorch AI Factory, Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains. In a nutshell, Flash is the production-grade research framework you always dreamed of but didn't have time to build. All data loading in Flash is performed via a from_* classmethod on a DataModule. Which DataModule to use and which from_* methods are available depends on the task you want to perform. -
24
Deep learning time series forecasting
Deep learning PyTorch library for time series forecasting
...Currently, Task-TS from CoronaWhy primarily maintains this repository. Pull requests are welcome. Historically, this repository provided open-source benchmarks and codes for flash flood and river flow forecasting. Full transformer (SimpleTransformer in model_dict): The full original transformer with all 8 encoder and decoder blocks. Requires passing the target in at inference. -
25
html2canvas
A JavaScript HTML screenshot renderer
html2canvas is a JavaScript HTML renderer. The script provides you with the tools to take screenshots of webpages directly on the browser. The screenshot is based on the DOM and therefore, it may not be 100% accurate to the real representation, given that it is not an actual screenshot, but a type of screenshot built based on the available data and information of the page. The script renders such page as a canvas image, by reading the DOM and the different styles of the featured elements. It...