Search Results for "performance" - Page 19
Sort By:
Showing 1009 open source projects for "performance"
View related business solutions-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
1
LongWriter
Unleashing 10,000+ Word Generation from Long Context LLMs
LongWriter is an open-source framework and set of large language models designed to enable ultra-long text generation that can exceed 10,000 words while maintaining coherence and structure. Traditional large language models can process large inputs but often struggle to generate long outputs due to limitations in training data and alignment strategies. LongWriter addresses this challenge by introducing a specialized dataset and training approach that encourages models to produce longer... -
2
xLSTM
Neural Network architecture based on ideas of the original LSTM
...By introducing innovations such as matrix-based memory and improved normalization techniques, xLSTM improves the ability of recurrent networks to capture long-range dependencies in sequential data. The architecture aims to provide competitive performance with transformer-based models while maintaining advantages such as linear computational scaling and efficient memory usage for long sequences. Researchers have demonstrated that xLSTM models can scale to billions of parameters and large training datasets while maintaining efficient inference speeds. -
3
TigerBot
TigerBot: A multi-language multi-task LLM
TigerBot is an open-source family of large language models designed to support multilingual and multi-task natural language processing applications. The project focuses on building high-performance models capable of handling both English and Chinese tasks while maintaining strong reasoning and conversational abilities. TigerBot models are based on modern transformer architectures and are trained on large datasets that cover multiple domains and languages. The project provides both base models and chat-optimized variants that can be used for dialogue systems, question answering, and general language understanding tasks. ... -
4
MatMul-Free LM
Implementation for MatMul-free LM
...Since matrix multiplication is one of the most computationally expensive components of modern language models, the project explores alternative computational strategies that reduce hardware requirements while maintaining comparable performance. The architecture relies on quantization-aware training and lightweight operations to replace conventional dense matrix multiplications with more efficient alternatives. These optimizations can significantly reduce memory consumption and potentially improve computational efficiency during both training and inference. The repository provides implementations of models at several parameter scales and includes tools for experimenting with the architecture using modern machine learning frameworks. -
Stop vibe-debugging.AppSignal's MCP server hands Claude, Cursor, or Zed your real errors, traces, and the deploy that shipped them. AI writes the fix; you review the diff.
-
5
Skywork-R1V4
Skywork-R1V is an advanced multimodal AI model series
...Instead of retraining both language and vision models from scratch, the framework uses a lightweight visual projection layer that connects a pretrained vision backbone with a reasoning-capable language model. This design allows the model to analyze images while maintaining strong textual reasoning performance, enabling tasks such as solving visual math problems, interpreting scientific diagrams, and answering questions about images. -
6
Torch Pruning
DepGraph: Towards Any Structural Pruning
Torch-Pruning is an open-source toolkit designed to optimize deep neural networks by performing structural pruning directly within PyTorch models. The library focuses on reducing the size and computational cost of neural networks by removing redundant parameters and channels while maintaining model performance. It introduces a graph-based algorithm called DepGraph that automatically identifies dependencies between layers, allowing parameters to be pruned safely across complex architectures. This dependency analysis makes it possible to prune large networks such as transformers, convolutional networks, and diffusion models without breaking the computational graph. ... -
7
Chat with LLMs Everywhere
Run PyTorch LLMs locally on servers, desktop and mobile
...TorchChat supports running models through Python interfaces as well as integrating them directly into native applications written in languages such as C or C++. The project also demonstrates how modern LLMs like LLaMA-style models can be deployed locally while maintaining good performance across different hardware platforms. -
8
LightLLM
LightLLM is a Python-based LLM (Large Language Model) inference
LightLLM is a high-performance inference and serving framework designed specifically for large language models, focusing on lightweight architecture, scalability, and efficient deployment. The framework enables developers to run and serve modern language models with significantly improved speed and resource efficiency compared to many traditional inference systems. -
9
Agents 2.0
An Open-source Framework for Data-centric Language Agents
Agents is an open-source framework designed to build and train autonomous language agents through a data-centric and learning-oriented architecture. The project introduces a concept known as agent symbolic learning, which treats an agent pipeline similarly to a neural network computational graph. In this framework, each node in the pipeline represents a step in the reasoning or action process, while prompts and tools act as adjustable parameters analogous to neural network weights. During... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
Intel LLM Library for PyTorch
Accelerate local LLM inference and finetuning
...Built as an extension of the PyTorch ecosystem, the library enables developers to run modern transformer models efficiently on Intel CPUs, GPUs, and specialized AI accelerators. The framework provides hardware-aware optimizations and low-precision computation techniques that significantly improve the performance of large language models while reducing memory consumption. IPEX-LLM supports a wide range of popular models, including architectures such as LLaMA, Mistral, Qwen, and other transformer-based systems. The library can integrate with common AI frameworks and serving tools such as Hugging Face Transformers, LangChain, and vLLM, allowing developers to incorporate optimized inference into existing pipelines. -
11
Claude Code Templates
CLI tool for configuring and monitoring Claude Code
Claude Code Templates is a popular open-source CLI tool and template ecosystem designed to streamline how developers work with Anthropic’s Claude Code by providing a rich catalog of ready-to-use code templates, AI agents, custom commands, settings, hooks, and external integrations that can be installed interactively or via the command line. It lets you quickly scaffold domain-specific AI agents (like security auditors, performance optimizers, or database architects), fill in consistent project configurations, and embed automated workflows without reinventing the wheel for each new project. The templates and components are organized by workflow so teams can adopt best practices for testing, deployment, documentation, DevOps automation, and more, all powered by Claude’s agent SDK. ... -
12
Agent Lightning
The absolute trainer to light up AI agents
...Agent-Lightning introduces a lightweight training pipeline that observes agents’ execution traces, converts them into structured data, and feeds them into training algorithms, enabling users to improve agent behaviors systematically. The project emphasizes minimalist integration, so you can drop this into existing systems without extensive rewrites, focusing instead on iterative performance improvement. -
13
Chinese-XLNet
Chinese XLNet pre-trained model
...This model is trained on large-scale Chinese text datasets to learn linguistic patterns, long-range dependencies, and semantic nuance typical of Chinese writing, making it useful for tasks like text classification, question answering, named entity recognition, and language generation. Chinese-XLNet offers an alternative to models like BERT by emphasizing autoregressive and permutation-based learning, which can lead to performance improvements on certain benchmarks and tasks. -
14
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... -
15
Advanced RAG Techniques
Advanced techniques for RAG systems
...It includes hands-on Jupyter notebooks and runnable scripts that show how to implement ideas like optimizing chunk sizes, proposition chunking, HyDE/HyPE query transformations, fusion retrieval, reranking, and ensemble retrieval. There is also an evaluation section that demonstrates how to measure RAG performance and compare different configurations in a systematic way. -
16
EKS Best Practices
A best practices guide for day 2 operations
The Amazon EKS Best Practices Guide is a public repository containing comprehensive documentation and guidance for operating production-grade Kubernetes clusters on AWS’s managed service, Amazon EKS. Rather than a code library, it serves as a reference catalogue of patterns, anti-patterns, checklists and architectures across domains such as security, reliability, scalability, networking, cost optimization and hybrid cloud deployments. The repository is maintained by AWS but open to... -
17
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, streaming, and upsert—making it easy to keep embeddings synchronized as content changes. ... -
18
RLax
Library of JAX-based building blocks for reinforcement learning agents
...It supports both on-policy and off-policy learning, as well as value-based, policy-based, and model-based approaches. RLax is fully JIT-compilable with JAX, enabling high-performance execution across CPU, GPU, and TPU backends. The library implements tools for Bellman equations, return distributions, general value functions, and policy optimization in both continuous and discrete action spaces. It integrates seamlessly with DeepMind’s Haiku (for neural network definition) and Optax (for optimization), making it a key component in modular RL pipelines. -
19
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
...The broader project includes examples, tests, a server component, and public posts describing cross-engine sharing and inter-GPU KV transfers. These capabilities aim to lower latency, cut GPU cycles, and stabilize performance for production workloads with overlapping prompts or retrieval-augmented contexts. The end result is a cache fabric for LLMs that complements engines rather than replacing them. -
20
Shumai
Fast Differentiable Tensor Library in JavaScript & TypeScript with Bun
Shumai is an experimental differentiable tensor library for TypeScript and JavaScript, developed by Facebook Research. It provides a high-performance framework for numerical computing and machine learning within modern JavaScript runtimes. Built on Bun and Flashlight, with ArrayFire as its numerical backend, Shumai brings GPU-accelerated tensor operations, automatic differentiation, and scientific computing tools directly to JavaScript developers. It allows seamless integration of machine learning, deep learning, and custom differentiable programs into web-based or server-side environments without relying on Python frameworks. ... -
21
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well... -
22
DLRM
An implementation of a deep learning recommendation model (DLRM)
...The architecture combines dense (MLP) and sparse (embedding) branches, then interacts features via dot product or feature interactions before passing through further dense layers to predict click-through, ranking scores, or conversion probabilities. The implementation is optimized for performance at scale, supporting multi-GPU and multi-node execution, quantization, embedding partitioning, and pipelined I/O to feed huge embeddings efficiently. 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. -
23
MoCo (Momentum Contrast)
Self-supervised visual learning using momentum contrast in PyTorch
...The core idea of MoCo is to maintain a dynamic dictionary with a momentum-updated encoder, allowing efficient contrastive learning across large batches. The repository includes implementations for both MoCo v1 and MoCo v2, the latter improving training stability and performance through architectural and augmentation enhancements. Training is optimized for distributed multi-GPU environments, using DistributedDataParallel for speed and simplicity. -
24
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). -
25
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
...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. Efficient architecture and memory design for large-scale reasoning. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process.
