Search Results for "throughput" - Page 2
Sort By:
Showing 84 open source projects for "throughput"
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.
-
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.
-
1
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B),... -
2
Loki Mode
Multi-agent autonomous startup system for Claude Code
...By supporting multiple AI providers (like Claude Code, OpenAI Codex CLI, and Google Gemini CLI), loki-mode dynamically selects and spawns only the needed agents for a given project, optimizing computational resources and task throughput. Its Reason-Act-Reflect-Verify (RARV) cycle with self-verification loops emphasizes quality and resilience, automating end-to-end development lifecycles. -
3
Pocket TTS
A TTS that fits in your CPU (and pocket)
...Because it is CPU-oriented, it fits well in server environments where GPU access is limited, in desktop apps, or in edge deployments where simplicity matters more than maximum throughput. It also emphasizes developer ergonomics, providing a straightforward API surface that can be integrated into pipelines, assistants, accessibility tools, or batch generation scripts. -
4
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
...The platform enables developers to deploy trained models quickly using optimized inference pipelines that support GPUs, specialized AI accelerators, and other hardware architectures. FastDeploy includes advanced acceleration technologies such as speculative decoding, multi-token prediction, and efficient KV cache management to improve throughput and latency during inference. It also offers compatibility with OpenAI-style APIs and vLLM-like interfaces, allowing developers to integrate deployed models easily into existing applications and services. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
xFormers
Hackable and optimized Transformers building blocks
xformers is a modular, performance-oriented library of transformer building blocks, designed to allow researchers and engineers to compose, experiment, and optimize transformer architectures more flexibly than monolithic frameworks. It abstracts components like attention layers, feedforward modules, normalization, and positional encoding, so you can mix and match or swap optimized kernels easily. One of its key goals is efficient attention: it supports dense, sparse, low-rank, and... -
6
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. This approach has been shown to deliver lossless acceleration on models like Qwen3-8B by combining block diffusion techniques with efficient batching, making it ideal for applications where latency and cost matter. The project includes support for multiple draft models, example integration code, and scripts to benchmark performance, and it is structured to work with popular model serving stacks like SGLang and the Hugging Face Transformers ecosystem. -
7
fairseq2
FAIR Sequence Modeling Toolkit 2
fairseq2 is a modern, modular sequence modeling framework developed by Meta AI Research as a complete redesign of the original fairseq library. Built from the ground up for scalability, composability, and research flexibility, fairseq2 supports a broad range of language, speech, and multimodal content generation tasks, including instruction fine-tuning, reinforcement learning from human feedback (RLHF), and large-scale multilingual modeling. Unlike the original fairseq—which evolved into a... -
8
Modular Platform
The Modular Platform (includes MAX & Mojo)
...It is closely associated with the Mojo programming language and related tooling that aims to combine Python usability with systems-level performance. Modular’s ecosystem is designed to simplify deployment of AI workloads across heterogeneous hardware while maximizing throughput. The repository reflects an effort to modernize the AI development pipeline from compilation to runtime execution. Overall, Modular represents an ambitious attempt to unify performance engineering and developer ergonomics for large-scale AI systems. -
9
Qwen-Agent
Agent framework and applications built upon Qwen>=3.0
Qwen-Agent is a framework for building applications / agents using Qwen models (version 3.0+). It provides components for instruction following, tool usage (function calling), planning, memory, RAG (retrieval augmented generation), code interpreter, etc. It ships with example applications (Browser Assistant, Code Interpreter, Custom Assistant), supports GUI front-ends, backends, server setups. Agent workflow can maintain context / memory to perform multi-turn or more complex logic over time.... -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
10
VidGear
A High-performance cross-platform Video Processing Python framework
...The framework is built around modular components called “gears,” each responsible for tasks such as video capture, streaming, encoding, and network transmission. It supports multi-threaded and asynchronous operations, enabling low-latency processing and efficient handling of high-throughput video streams. VidGear is designed to handle a wide range of use cases, including live streaming, video stabilization, screencasting, and distributed video systems. Its emphasis on simplicity allows developers to implement advanced multimedia pipelines with minimal code while maintaining performance and flexibility. -
11
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... -
12
NeMo Retriever Library
Document content and metadata extraction microservice
...The system is built on NVIDIA NIM microservices, enabling high-performance parallel processing and efficient handling of large datasets. It supports multiple extraction strategies for different document formats, balancing accuracy and throughput depending on the use case. Additionally, it can generate embeddings for extracted content and integrate with vector databases like Milvus, making it well-suited for retrieval-augmented generation pipelines. -
13
ZeusDB Vector Database
Blazing-fast vector DB with similarity search and metadata filtering
ZeusDB is a vector database built for fast, scalable similarity search with strong production ergonomics. It combines high-performance approximate nearest neighbor indexes with clean APIs and metadata filtering so applications can retrieve semantically relevant items at low latency. The storage layer is designed for durability and growth, supporting sharding, replication, and background compaction while keeping query tails predictable. Developers get multiple ingestion paths—batch,... -
14
Orpheus TTS
Towards Human-Sounding Speech
...The project ships both pretrained and finetuned English models, as well as a family of multilingual models released as a research preview, and includes data-processing scripts so users can train or finetune their own variants. Inference is provided through a Python package that uses vLLM under the hood for high-throughput, low-latency generation, including streaming examples that show how to generate audio chunks in real time. The maintainers provide Colab notebooks, a standardized prompting format, and one-click deployment via Baseten for production-grade, FP8/FP16 optimized inference with ~200 ms streaming latency. -
15
TokenSpeed
TokenSpeed is a speed-of-light LLM inference engine
...It aims to combine TensorRT-LLM-level speed with vLLM-level usability, making it relevant for teams that need fast generation without sacrificing developer ergonomics. The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. It builds on ideas and components from the broader open-source inference ecosystem while presenting its own execution stack. TokenSpeed is useful for developers building local or server-side LLM infrastructure for agents, coding systems, and high-volume AI applications. ... -
16
Torrra
A Python tool that lets you search and download torrents
...Users can add, pause, prioritize, and remove torrents dynamically, while the client intelligently manages piece selection, peer discovery, and bandwidth allocation to optimize download throughput. Torrra also includes hooks for event monitoring and status reporting, enabling third-party tools to visualize torrent progress or integrate with home automation dashboards. -
17
gain
Asyncio-based Python framework for building fast web crawling spiders
Gain is a Python web crawling framework designed to simplify the process of building efficient and scalable web scrapers. It is built on top of asynchronous technologies such as asyncio, aiohttp, and uvloop to support high-performance crawling with concurrent network requests. It provides a structured framework for creating spiders that can navigate websites, extract structured data, and process the collected results. Developers define crawlers using components such as spiders, parsers, and... -
18
MaxText
A simple, performant and scalable Jax LLM
...It is optimized to run efficiently on Google Cloud TPUs and GPUs, enabling researchers and engineers to train models ranging from small experiments to extremely large distributed workloads. The framework focuses on simplicity while still supporting advanced techniques such as model sharding, distributed computation, and high-throughput training pipelines. MaxText includes ready-to-use configurations and reproducible training examples that help developers understand how to deploy large-scale AI workloads with modern machine learning infrastructure. -
19
bitnet.cpp
Official inference framework for 1-bit LLMs
...BitNet is built to scale across architectures, with configurable kernels and tiling strategies that adapt to different hardware, and it supports large models with impressive throughput even on modest resources. -
20
nanochat
The best ChatGPT that $100 can buy
nanochat is a from-scratch, end-to-end “mini ChatGPT” that shows the entire path from raw text to a chatty web app in one small, dependency-lean codebase. The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and... -
21
DLRM
An implementation of a deep learning recommendation model (DLRM)
...It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput. -
22
Smallpond
A lightweight data processing framework built on DuckDB and 3FS
...Users write Python-like code (via DataFrame APIs or SQL strings) to express their transformations; behind the scenes, tasks are scheduled (often via Ray) and pushed into DuckDB instances operating on partitioned data. Because the storage layer (3FS) is optimized for random access and high throughput, smallpond can shuffle data, repartition, and manage intermediate results across nodes. -
23
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.... -
24
Matrix
Multi-Agent daTa geneRation Infra and eXperimentation framework
Matrix is a distributed, large-scale engine for multi-agent synthetic data generation and experiments: it provides the infrastructure to run thousands of “agentic” workflows concurrently (e.g. multiple LLMs interacting, reasoning, generating content, data-processing pipelines) by leveraging distributed computing (like Ray + cluster management). The idea is to treat data generation as a “data-to-data” transformation: each input item defines a task, and the runtime orchestrates asynchronous,... -
25
marqo
Tensor search for humans
A tensor-based search and analytics engine that seamlessly integrates with your applications, websites, and workflows. Marqo is a versatile and robust search and analytics engine that can be integrated into any website or application. Due to horizontal scalability, Marqo provides lightning-fast query times, even with millions of documents. Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. It can seamlessly handle image-to-image, image-to-text and...
