Search Results for "cache memory simulator"
Sort By:
Showing 23 open source projects for "cache memory simulator"
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 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
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 during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. ... -
2
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer 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. ... -
3
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
...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. -
4
claude-obsidian
Claude + Obsidian knowledge companion
claude-obsidian is an AI-powered knowledge engine that transforms an Obsidian vault into a self-organizing, continuously evolving wiki. Instead of acting as a simple chat assistant, it autonomously creates, links, and maintains structured knowledge based on user inputs and external sources. The system follows the LLM Wiki pattern, where information is stored as persistent markdown files that grow richer over time through cross-referencing and synthesis. It includes features such as... -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
oMLX
LLM inference server with continuous batching & SSD caching
...It serves text models, vision-language models, OCR models, embeddings, and rerankers through OpenAI- and Anthropic-compatible APIs. Continuous batching allows concurrent requests, while a tiered KV cache keeps active data in RAM and moves colder blocks to SSD for reuse. Models can be pinned, unloaded manually, or evicted automatically when memory runs low. A web dashboard provides monitoring, chat, downloads, benchmarks, integrations, and per-model settings. It also supports tool calling, structured output, MCP integration, and experimental multi-Mac inference. -
6
django-health-check
a pluggable app that runs a full check on the deployment
The primary intended use case is to monitor conditions via HTTP(S), with responses available in HTML and JSON formats. When you get back a response that includes one or more problems, you can then decide the appropriate course of action, which could include generating notifications and/or automating the replacement of a failing node with a new one. If you are monitoring health in a high-availability environment with a load balancer that returns responses from multiple nodes, please note that... -
7
mac code
Claude Code, but it runs on your Mac for free
mac code is a local AI coding agent designed to run large language models directly on Apple Silicon machines without relying on cloud services, effectively transforming a Mac into a self-contained AI development environment. The project focuses on enabling models that traditionally exceed available RAM to run efficiently by streaming model weights from SSD storage, thereby overcoming hardware limitations through innovative memory management techniques. It operates as a CLI-based assistant... -
8
TensorRT LLM
TensorRT LLM provides users with an easy-to-use Python API
TensorRT-LLM is an open-source high-performance inference library specifically designed to optimize and accelerate large language model deployment on NVIDIA GPUs. It provides a Python-based API built on top of PyTorch that allows developers to define, customize, and deploy LLMs efficiently across a variety of hardware configurations, from single GPUs to large multi-node clusters. The library focuses on maximizing throughput and minimizing latency through advanced techniques such as... -
9
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
BigMac is an open-source toolkit for pipeline-parallel training of multimodal large language models. It preserves optimized language-model pipeline schedules while placing encoder and generator work around them. This design reduces activation memory without bringing back cross-module pipeline bubbles. Its scheduler creates global operator plans, while its executor runs those plans through a shared schedule abstraction. A Megatron-Core reference backend and Qwen3 and Qwen3-VL tutorials help developers connect the approach to real training workflows. The simulator lets researchers visualize schedules, compare pipeline strategies, and model timing imbalances caused by compute cost, input size, or uneven stage partitioning. ... -
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.
-
10
LingBot-World
Advancing Open-source World Models
LingBot-World is an open-source, high-fidelity world simulator designed to advance the state of world models through video generation. Built on top of Wan2.2, it enables realistic, dynamic environment simulation across diverse styles, including real-world, scientific, and stylized domains. LingBot-World supports long-term temporal consistency, maintaining coherent scenes and interactions over minute-level horizons. With real-time interactivity and sub-second latency at 16 FPS, it is... -
11
Zappa - Serverless Python
Serverless Python
...With Zappa, each request is given its own virtual HTTP "server" by Amazon API Gateway. AWS handles the horizontal scaling automatically, so no requests ever time out. Each request then calls your application from a memory cache in AWS Lambda and returns the response via Python's WSGI interface. After your app returns, the "server" dies. -
12
SweptPC
SweptPC — Free Portable Windows PC Cleaner
SweptPC is a free, portable Windows PC cleaner that removes junk files, browser cache, temp files and more — no installation required. Built by VaultSoft, the team behind PulseMonitor. ―――――――――――――――――――――― WHAT IT CLEANS ―――――――――――――――――――――― 🗂 Windows Temp Files ⚡ Prefetch Cache 📋 Windows Log Files ♻ Recycle Bin 🌐 Chrome, Edge & Firefox Cache 💬 Microsoft Teams & Discord Cache 🖼 Windows Thumbnail Cache 🔄 Windows Update Cache 💾 Memory Dump Files ―――――――――――――――――――――― HOW TO USE ―――――――――――――――――――――― 1. ... -
13
RWKV
RNN with great LLM performance
...The project is built around the idea that a model can be trained in a parallelizable way like a GPT-style transformer while running inference with recurrent efficiency. This gives RWKV important advantages for long-context use, including lower memory pressure and no traditional key-value cache requirement. The repository includes training code, model notes, research material, and references to current RWKV weights. Its main value is providing the foundation for experimenting with efficient large language models that combine transformer-like scalability with RNN-like runtime behavior. -
14
Zappa
Serverless Python
...With Zappa, each request is given its own virtual HTTP "server" by Amazon API Gateway. AWS handles the horizontal scaling automatically, so no requests ever time out. Each request then calls your application from a memory cache in AWS Lambda and returns the response via Python's WSGI interface. After your app returns, the "server" dies. -
15
gitfs
Version controlled file system
gitfs is a FUSE file system that fully integrates with git. You can mount a remote repository's branch locally, and any subsequent changes made to the files will be automatically committed to the remote. gitfs was developed by the awesome engineering team at Presslabs, a Managed WordPress Hosting provider. gitfs was designed to bring the full powers of git to everyone, no matter how little they know about versioning. A user can mount any repository and all their changes will be automatically... -
16
N.Tesla
Numerical Transient Simulator for Power System
...N.Tesla is an open source project to provide students and researchers of EE with a tool to implement new models for power system study and research. N.Tesla is short for Numerical TransiEnt SimuLAtor for power system and is in memory of Nikola Tesla, one the greatest scientists in alternating current power system. If you have any questions, please contact the author by send email to [lichgang AT gmail DOT com] or leave feedback in the Discussion forum. Mailing List for N.Tesla: http://www.freelists.org/list/ntesla Mailing List for N.Tesla Developer: http://www.freelists.org/list/ntesla-dev -
17
ppc_sim_booke
e500v2 simulator
An experimental ISS for freescale's e500v2 core. It is meant to simulate only cpu and memory subsystem and is purely intended for academic/learning purposes only. -
18
pykb
Python Killboard Platform for EVE Online
...Aggregates exist along with code to maintain them to enable high speed reports for summarized data. A point calculation system is included as is support for parsing German and Russian kill mail text. Caching exists in two forms, a basic in memory dict based caching system suitable for single process tasks and integration with uwsgi's powerful and fast built in cache. Utility modules are provided for adding in killmails, backfilling killmails and dumping them via the command line. These also serve as reusable code for web apps or at least as usage examples. A sample web app using pykb is included. -
19
Infinispan
High performance distributed in-memory key/value store
Infinispan is an open source, Java based data grid platform. ***IMPORTANT*** Starting with Infinispan 5.0.0.FINAL, Infinispan releases are no longer hosted in Sourceforge. They can now be located in www.jboss.org/infinispan/downloads -
20
Framework for making Windows applications that are one .exe file in AutoHotKey_L,C++,C#, VB.NET,Java,Groovy,Common Lisp,Nemerle,Ruby,Python,PHP,Lua,Tcl,Perl,Jint,S#,WSH VBScript,HTML/JavaScript/CSS,COM, PowerShell without compiling . For .NET 4.
-
21
RoxBird is a advanced graphical download manager. It can accelerate your download speed upto 40% than your normal speed. Among others its key-features include file-browser, Pre-viewer, recursive downloading,Scheduling & Queues, Write-cache, and more.
-
22
CDNsim is a GNU/LINUX simulation tool for CDNs, written in C++ (core) and python (GUI wizard). It models: redirection policies, cache policies, TCP/IP, batch simulations, statistics extraction and more. CDNsim is uses the OMNet++ library
-
23
Video DeDup
Find duplicate videos by content
...Parse a video directory to create one image every n seconds, then identify duplicate images and show possible video duplicates for manual analysis. . 1f_parse scan video source folder, replicate with ffmpeg an image folder, then for each image create a fingerprint. . CompareV2 perform the fingerprints comparison and works in memory with constant memory usage. It is folder agnostic and parse fingerprints ordered by source file name. Since 201906 in free Pascal for x3 speed and less memory usage in multi-threading. . 3h_analyse is folder agnostic by first loading in memory current source and image folder. Then a lot of options and cache mechanism enable to get correct performance. ...
- Previous
- You're on page 1
- Next
