Search Results for "memory usage"
Sort By:
Showing 25 open source projects for "memory usage"
View related business solutions-
$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.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of... -
2
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. 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. ... -
3
xLSTM
Neural Network architecture based on ideas of the original LSTM
...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. -
4
GPU Hot
Real-time NVIDIA GPU dashboard
...The project offers a self-hosted web interface that streams hardware metrics directly from GPU servers, enabling developers, ML engineers, and system administrators to observe GPU utilization and system behavior in real time through a browser. The dashboard collects and displays a wide range of performance metrics including temperature, memory usage, power consumption, clock speeds, fan speed, and active processes. It can scale from monitoring a single GPU workstation to large distributed environments with dozens or even hundreds of GPUs by running lightweight containers on each node and aggregating the data centrally. -
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
Tencent-Hunyuan-Large
Open-source large language model family from Tencent Hunyuan
...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 (~50%) while maintaining precision. High benchmarking performance on tasks like MMLU, MATH, CMMLU, C-Eval, etc. -
6
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch
bitsandbytes is an open-source library designed to make training and inference of large neural networks more efficient by dramatically reducing memory usage. Built primarily for the PyTorch ecosystem, the library introduces advanced quantization techniques that allow models to operate using reduced numerical precision while maintaining high accuracy. These optimizations enable large language models and other deep learning architectures to run on hardware with limited memory resources, including consumer-grade GPUs. ... -
7
PicoLM
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
PicoLM is an open-source inference framework designed to run large language models on extremely constrained hardware environments such as inexpensive single-board computers and embedded systems. The project focuses on enabling efficient local inference by optimizing memory usage, computation, and system dependencies so that relatively large models can operate on devices with minimal RAM. It is written primarily in C and designed with a minimalist architecture that removes unnecessary dependencies and external libraries. The runtime is capable of running language models with billions of parameters on devices with only a few hundred megabytes of memory, which is significantly lower than typical LLM infrastructure requirements. ... -
8
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... -
9
PowerInfer
High-speed Large Language Model Serving for Local Deployment
PowerInfer is a high-performance inference engine designed to run large language models efficiently on personal computers equipped with consumer-grade GPUs. The project focuses on improving the performance of local AI inference by optimizing how neural network computations are distributed between CPU and GPU resources. Its architecture exploits the observation that only a subset of neurons in large models are frequently activated, allowing the system to preload frequently used neurons into... -
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
Flowise
Drag & drop UI to build your customized LLM flow
Open source UI visual tool to build your customized LLM flow using LangchainJS, written in Node Typescript/Javascript. Conversational agent for a chat model which utilizes chat-specific prompts and buffer memory. Open source is the core of Flowise, and it will always be free for commercial and personal usage. Flowise support different environment variables to configure your instance. You can specify the following variables in the .env file inside the packages/server folder. -
11
llama.cpp
LLM inference in C/C++
llama.cpp is a high-performance C and C++ project for running large language models locally and in the cloud with minimal setup. It is built around efficient inference, broad hardware support, and the GGUF model format. The project supports many model families and has become a major foundation for local AI tools, model serving, and embedded inference workflows. It provides command-line tools, a server mode with an OpenAI-compatible API style, model conversion utilities, and extensive backend... -
12
llm.c
LLM training in simple, raw C/CUDA
llm.c is a minimalist, systems-level implementation of a small transformer-based language model in C that prioritizes clarity and educational value. By stripping away heavy frameworks, it exposes the core math and memory flows of embeddings, attention, and feed-forward layers. The code illustrates how to wire forward passes, losses, and simple training or inference loops with direct control over arrays and buffers. Its compact design makes it easy to trace execution, profile hotspots, and... -
13
Qwen
The official repo of Qwen chat & pretrained large language model
Qwen is a series of large language models developed by Alibaba Cloud, consisting of various pretrained versions like Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B. These models, which range from smaller to larger configurations, are designed for a wide range of natural language processing tasks. They are openly available for research and commercial use, with Qwen's code and model weights shared on GitHub. Qwen's capabilities include text generation, comprehension, and conversation, making it a... -
14
LangChain for Java
LangChain4j is an open-source Java library
LangChain for Java is an open-source Java framework designed to simplify the development of applications powered by large language models. The library provides a unified API that allows developers to connect Java applications to multiple AI providers and embedding databases without having to implement separate integrations for each service. Its architecture includes abstractions for prompts, chat interactions, document processing, embeddings, and vector storage, enabling developers to build... -
15
AgentGuide
AI Agent Development Guide, LangGraph in Action, Advanced RAG
...Instead of presenting scattered resources, the repository organizes them into a systematic learning roadmap that guides learners from foundational concepts to advanced AI agent systems. The guide covers topics such as agent frameworks, retrieval-augmented generation systems, multi-agent collaboration, memory management, and tool usage. It also includes practical projects, interview preparation materials, and curated research papers related to AI agents and LLM engineering. The project is designed not only for learning but also for career preparation, helping developers understand how to build portfolio projects and prepare for AI engineering roles. -
16
Chitu
High-performance inference framework for large language models
...Chitu is designed to scale from small single-machine deployments to large distributed clusters that handle high volumes of concurrent inference requests. The system also includes performance optimizations for large models, including support for quantized formats and efficient computation operators that reduce memory usage and latency. Its architecture aims to support enterprise adoption by ensuring stable long-term operation under production workloads. -
17
Extractous
Fast and efficient unstructured data extraction
...Its purpose is to extract text and metadata efficiently from formats such as PDF, Word, HTML, email archives, images, and more, without depending on external APIs or separate parsing servers. The project emphasizes performance and low memory usage, and its maintainers describe it as a local-first alternative to heavier extraction stacks. For broader format support, the system combines its Rust core with ahead-of-time compiled Apache Tika shared libraries, which allows it to extend parsing coverage while still avoiding traditional server-based overhead. It also supports OCR for images and scanned documents through Tesseract, making it useful for document ingestion pipelines that include image-based or scanned inputs. -
18
LLM-Pruner
On the Structural Pruning of Large Language Models
LLM-Pruner is an open-source framework designed to compress large language models through structured pruning techniques while maintaining their general capabilities. Large language models often require enormous computational resources, making them expensive to deploy and inefficient for many practical applications. LLM-Pruner addresses this issue by identifying and removing non-essential components within transformer architectures, such as redundant attention heads or feed-forward... -
19
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.... -
20
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds... -
21
Punica
Serving multiple LoRA finetuned LLM as one
Punica is a system designed to efficiently serve multiple LoRA-fine-tuned large language models within a shared GPU environment. LoRA is a parameter-efficient fine-tuning method that allows developers to adapt large pretrained models to specific tasks by adding lightweight adapter layers rather than retraining the entire model. Punica introduces a serving architecture that allows multiple LoRA adapters to share the same base model during inference, significantly reducing memory consumption... -
22
Firefly LLM
A large model training tool that supports training large models
Firefly is an open-source framework designed to simplify the training and fine-tuning of large language models through a unified and configurable workflow. The project provides a comprehensive environment where developers can perform tasks such as model pre-training, instruction tuning, and preference optimization using widely adopted machine learning techniques. Its architecture supports both full-parameter training and parameter-efficient strategies like LoRA and QLoRA, making it suitable... -
23
gpu_poor
Calculate token/s & GPU memory requirement for any LLM
gpu_poor is an open-source tool designed to help developers determine whether their hardware is capable of running a specific large language model and to estimate the performance they can expect from it. The project focuses on calculating GPU memory requirements and predicted inference speed for different models, hardware configurations, and quantization strategies. By analyzing factors such as model size, context length, batch size, and GPU specifications, the system estimates how much VRAM... -
24
ChatLLM Web
Chat with LLM like Vicuna totally in your browser with WebGPU
...To use this app, you need a browser that supports WebGPU, such as Chrome 113 or Chrome Canary. Chrome versions ≤ 112 are not supported. You will need a GPU with about 6.4GB of memory. If your GPU has less memory, the app will still run, but the response time will be slower. The first time you use the app, you will need to download the model. For the Vicuna-7b model that we are currently using, the download size is about 4GB. After the initial download, the model will be loaded from the browser cache for faster usage. -
25
MiMo-V2.5-Pro
Flagship MoE model for long-context agents and complex coding
...The model supports a 1 million token context window, enabling it to maintain coherence across long workflows involving thousands of tool calls and multi-step reasoning chains. Architecturally, it uses a hybrid attention system combining Sliding Window Attention and Global Attention to significantly reduce memory usage while preserving long-context performance. It also integrates multi-token prediction modules that accelerate inference and improve reinforcement learning efficiency. Trained on around 27 trillion tokens with FP8 mixed precision and refined through supervised fine-tuning, large-scale agentic reinforcement learning, and distillation.
- Previous
- You're on page 1
- Next
