Search Results for "latency" - Page 2
Sort By:
Showing 146 open source projects for "latency"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$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
Vision Agents
Open Vision Agents by Stream. Build voice and vision agents quickly
Vision Agents is an open-source Python framework for building real-time voice and video AI agents. It is designed for applications that need to watch, listen, understand, and respond with very low latency. The framework can combine vision models, speech models, LLMs, and real-time transport providers into one agent workflow. It supports use cases such as live coaching, telehealth, customer support, security monitoring, interactive video assistants, and voice-controlled tools. Vision Agents is model-agnostic, so developers can connect providers such as OpenAI, Gemini, Claude, Hugging Face, YOLO, Roboflow, and others. ... -
2
Parallax
Parallax is a distributed model serving framework
...A two-stage scheduling architecture determines how model layers are allocated to available hardware and how requests are routed across nodes during execution. This scheduling system optimizes latency, throughput, and hardware utilization even when nodes have different computational capabilities. The platform also supports model sharding and pipeline parallelism, allowing very large models to run across distributed resources. -
3
MobileCLIP
Implementation of "MobileCLIP" CVPR 2024
...It includes an iOS demo app and Core ML artifacts to showcase practical, offline photo search and classification on iPhone-class hardware. Project notes highlight latency/accuracy trade-offs, with MobileCLIP2 variants matching or surpassing larger baselines at notably lower parameter counts and runtime on mobile devices. A companion “mobileclip-dr” repository details large-scale, distributed data-generation pipelines used to reinforce datasets across billions of samples on thousands of GPUs. Overall, MobileCLIP emphasizes end-to-end practicality: scalable training, deployable models, and consumer-grade demos. -
4
CoreNet
CoreNet: A library for training deep neural networks
CoreNet is Apple’s internal deep learning framework for distributed neural network training, designed for high scalability, low-latency communication, and strong hardware efficiency. It focuses on enabling large-scale model training across clusters of GPUs and accelerators by optimizing data flow and parallelism strategies. CoreNet provides abstractions for data, tensor, and pipeline parallelism, allowing models to scale without code duplication or heavy manual configuration. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
Pathway
Python ETL framework for stream processing, real-time analytics, LLM
Pathway is an open-source framework designed for building real-time data applications using reactive and declarative paradigms. It enables seamless integration of live data streams and structured data into analytical pipelines with minimal latency. Pathway is especially well-suited for scenarios like financial analytics, IoT, fraud detection, and logistics, where high-velocity and continuously changing data is the norm. Unlike traditional batch processing frameworks, Pathway continuously updates the results of your data logic as new events arrive, functioning more like a database that reacts in real-time. ... -
6
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. -
7
DeepSpeed
Deep learning optimization library: makes distributed training easy
...Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. ... -
8
MiniCPM4
Ultra-Efficient LLMs on End Device
...Unlike traditional large-scale models that require extensive computational resources, MiniCPM4 focuses on delivering competitive reasoning and language capabilities while maintaining significantly lower latency and higher efficiency. It achieves this through optimized architectures, scalable training strategies, and techniques such as long-context pretraining and YaRN-based length extension, allowing it to handle sequences up to 128K tokens effectively. The model demonstrates strong performance across tasks such as long-text comprehension, reasoning, and general language generation, often outperforming similar-sized models in both speed and accuracy. ... -
9
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. FireRedTTS2 supports multilingual output and speaker flexibility, enabling scenarios that involve language switching, cross-lingual voice cloning, and expressive dialogue generation that maintains consistency over longer utterances. -
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
Fun Audio Chat
Large Audio Language Model built for natural interactions
...The system supports dynamic audio input and output, meaning it can handle different voices, tones, and conversational contexts without forcing users into typed interactions. With real-time streaming, it minimizes latency and delivers responses quickly, making it suitable for applications where responsiveness matters, such as interactive demos, accessibility tools, and conversational games. -
11
StreamSpeech
StreamSpeech is a seamless model for offline speech recognition
StreamSpeech is an “all-in-one” speech model designed to perform offline and simultaneous speech recognition, speech translation, and speech synthesis within a single unified architecture. Developed as part of an ACL 2024 paper, it targets streaming and low-latency scenarios where intermediate results and final translations or synthetic speech must be produced continuously as audio is being received. The model supports eight tasks: offline ASR, speech-to-text translation, speech-to-speech translation, and TTS, as well as their streaming or simultaneous counterparts, all handled by the same underlying system. ... -
12
FastVLM
This repository contains the official implementation of FastVLM
...The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
13
DeepEP
DeepEP: an efficient expert-parallel communication library
DeepEP is a communication library designed specifically to support Mixture-of-Experts (MoE) and expert parallelism (EP) deployments. Its core role is to implement high-throughput, low-latency all-to-all GPU communication kernels, which handle the dispatching of tokens to different experts (or shards) and then combining expert outputs back into the main data flow. Because MoE architectures require routing inputs to different experts, communication overhead can become a bottleneck — DeepEP addresses that by providing optimized GPU kernels and efficient dispatch/combining logic. ... -
14
Infinity
Low-latency REST API for serving text-embeddings
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting all sentence-transformer models and frameworks. Infinity is developed under MIT License. Infinity powers inference behind Gradient.ai and other Embedding API providers. -
15
HypoMux
Windows multi-NIC bandwidth aggregator
...Version 2 adds a virtual network adapter mode alongside the original system proxy mode for broader traffic handling. It also includes process-level routing rules so latency-sensitive apps can bypass aggregation while download-heavy apps use it. HypoMux is best suited for large Steam updates, download managers, browser downloads, and similar multi-connection workloads, not single-stream transfers. -
16
Bailing
Bailing is a voice dialogue robot similar to GPT-4o
...The project is modular: each core function — ASR, VAD, LLM, TTS — exists as a separately replaceable component, which allows flexibility in picking your preferred models depending on resources or languages. It aims to be light enough to run without a GPU, making it usable on modest hardware or edge devices, while still maintaining low latency and smooth interaction. Bailing includes a memory system, giving the assistant the ability to remember user preferences and context across sessions, which enables more personalized and context-aware conversations. -
17
Chatterbox
SoTA open-source TTS
...If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link). It delivers reliable performance with ultra-low latency of sub-200ms—ideal for production use in agents, applications, or interactive media. -
18
Universal Tool Calling Protocol (UTCP)
Official python implementation of UTCP. UTCP is an open standard
...It leverages a modular, plugin-based architecture built around Pydantic models and separates the core functionality into a lightweight client and extensible protocol plugins, enabling secure, scalable, and low-latency direct tool calls. A pluggable architecture allows developers to easily add new communication protocols, tool storage mechanisms, and search strategies without modifying the core library. -
19
Lemonade
Lemonade helps users run local LLMs with the highest performance
...The repository highlights easy onboarding with downloads, docs, and a Discord for support, suggesting an active user community. Messaging centers on squeezing maximum throughput/latency from modern accelerators without users having to hand-tune kernels or flags. Releases further reinforce the “server” framing, pointing developers toward a service that can be integrated into apps and tools. -
20
Code-Mode
Plug-and-play library to enable agents to call MCP and UTCP tools
...The repository contains both TypeScript and Python libraries, plus a code-mode-mcp component for integrating with MCP and UTCP ecosystems. Benchmarks in the README highlight improvements in latency and token cost for scenarios involving multiple tools, showing that code execution often outperforms traditional JSON-based function calling. -
21
SenseVoice
Multilingual speech recognition and audio understanding model
SenseVoice is a speech foundation model designed to perform multiple voice understanding tasks from audio input. It provides capabilities such as automatic speech recognition, spoken language identification, speech emotion recognition, and audio event detection within a single system. SenseVoice is trained on more than 400,000 hours of speech data and supports over 50 languages for multilingual recognition tasks. It is built to achieve high transcription accuracy while maintaining efficient... -
22
Qbot
AI-powered Quantitative Investment Research Platform
...It bundles a lightweight GUI client (built with wxPython) and a modular backend so researchers can iterate on strategies, run batch backtests, and validate ideas in a near-real simulated environment that models latency and slippage. The project places special emphasis on AI-driven strategies — including supervised learning, reinforcement learning and multi-factor models — and offers a “model zoo” and example strategies to help users get started. For evaluation and analysis, Qbot integrates reporting and visualization (tearsheets, metrics) so you can compare performance across runs and inspect trade-level behavior. ... -
23
VoxCPM2
Tokenizer-Free TTS for Multilingual Speech Generation
VoxCPM2 is an advanced open-source text-to-speech system that redefines speech synthesis by eliminating traditional tokenization and instead generating continuous speech representations through a diffusion-based autoregressive architecture. Built on top of the MiniCPM model family, it enables highly natural, expressive, and context-aware speech generation that adapts tone, emotion, and pacing directly from input text. The system is trained on massive multilingual datasets, enabling support... -
24
LLaMA 3
The official Meta Llama 3 GitHub site
This repository is the former home for Llama 3 model artifacts and getting-started code, covering pre-trained and instruction-tuned variants across multiple parameter sizes. It introduced the public packaging of weights, licenses, and quickstart examples that helped developers fine-tune or run the models locally and on common serving stacks. As the Llama stack evolved, Meta consolidated repositories and marked this one deprecated, pointing users to newer, centralized hubs for models,... -
25
RealtimeTTS
Converts text to speech in realtime
RealtimeTTS is a low-latency text-to-speech library built for real-time applications such as voice chat with LLMs, assistants, and interactive tools. It is designed around a streaming model: you can feed it text incrementally (for example, as an LLM responds) and get audio output almost immediately, which keeps end-to-end latency very low. The library is engine-agnostic and plugs into a wide range of cloud and local TTS systems, including OpenAI, ElevenLabs, Azure, Coqui, Piper, StyleTTS2, Edge TTS, Google TTS, system TTS and others, so you can swap providers without rewriting your pipeline. ...