Search Results for "wise memory optimizer"
Sort By:
Showing 23 open source projects for "wise memory optimizer"
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 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.
-
1
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
Model Optimizer is a unified library that provides state-of-the-art techniques for compressing and optimizing deep learning models to improve inference efficiency and deployment performance. It brings together multiple optimization strategies such as quantization, pruning, distillation, and speculative decoding into a single cohesive framework. The library is designed to reduce model size and computational requirements while maintaining accuracy, making it particularly valuable for deploying... -
2
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 VRAM. ... -
3
Model Explorer
A modern model graph visualizer and debugger
Model Explorer is a visual tool for exploring, debugging, and optimizing ML models deployed on edge devices. Developed by Google AI Edge, it offers a browser-based interface to inspect layer-wise performance, memory usage, and inference timing of TensorFlow Lite and other supported models. It’s a powerful utility for developers optimizing models for constrained environments. -
4
InMemoryDatasets.jl
Multithreaded package for working with tabular data in Julia
InMemoryDatasets.jl is a multithreaded package for data manipulation and is designed for Julia 1.6+ (64-bit OS). The core computation engine of the package is a set of customized algorithms developed specifically for columnar tables. -
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.
-
5
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
...The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. ... -
6
FSRS4Anki
A modern Anki custom scheduling based on Free Spaced Repetition
A modern spaced-repetition scheduler for Anki based on the Free Spaced Repetition Scheduler algorithm. -
7
LightGBM
Gradient boosting framework based on decision tree algorithms
LightGBM or Light Gradient Boosting Machine is a high-performance, open source gradient boosting framework based on decision tree algorithms. Compared to other boosting frameworks, LightGBM offers several advantages in terms of speed, efficiency and accuracy. Parallel experiments have shown that LightGBM can attain linear speed-up through multiple machines for training in specific settings, all while consuming less memory. LightGBM supports parallel and GPU learning, and can handle... -
8
Polars
Dataframes powered by a multithreaded, vectorized query engine
Polars is a high-performance, multi-language DataFrame library built in Rust using Apache Arrow. It delivers blazing-fast, vectorized, and parallel data manipulation with both eager and lazy execution, making it an excellent tool for data processing in Python, Rust, Node.js, R, and SQL contexts. -
9
verl-agent
Designed for training LLM/VLM agents via RL
...The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,... -
11
rw
rw calculates rank-width and rank-decompositions.
...It is based on ideas from "Computing rank-width exactly" by Sang-il Oum, "Sopra una formula numerica" by Ernesto Pascal, "Generation of a Vector from the Lexicographical Index" by B.P. Buckles and M. Lybanon and "Fast additions on masked integers" by Michael D. Adams and David S. Wise. On 2009's computers it works quite well up to graph sizes of about 28 nodes. Runtime and memory usage are exponential in the graph size. -
12
Thunderbird Anti Virus v4.0
Thunderbird Anti Virus Free Scanner v4.0
...Advanced Registry Optimizer: Safe, deep-hive cleaning with tailored configurations to remove unknown keys and repair system registries. -
13
ProPainter
Improving Propagation and Transformer for Video Inpainting
...It is designed to remove objects, complete missing regions, and fill masked areas in videos while preserving temporal consistency. The project accepts video input or split frames along with frame-wise masks that define the areas to reconstruct. It provides pretrained models, example inputs, inference scripts, and an interactive demo workflow for object removal. The repository also includes memory-efficient inference features to reduce GPU out-of-memory issues during video processing. ProPainter is useful for research, video editing experiments, object removal prototypes, and completion tasks where consistent motion is important. -
14
rathole
A lightweight and high-performance reverse proxy for NAT traversal
...High Performance Much higher throughput can be achieved than frp, and more stable when handling a large volume of connections. Low Resource Consumption Consumes much fewer memory than similar tools. See Benchmark. The binary can be as small as ~500KiB to fit the constraints of devices, like embedded devices as routers. Security Tokens of services are mandatory and service-wise. The server and clients are responsible for their own configs. With the optional Noise Protocol, encryption can be configured at ease. ... -
15
FairScale
PyTorch extensions for high performance and large scale training
FairScale is a collection of PyTorch performance and scaling primitives that pioneered many of the ideas now used for large-model training. It introduced Fully Sharded Data Parallel (FSDP) style techniques that shard model parameters, gradients, and optimizer states across ranks to fit bigger models into the same memory budget. The library also provides pipeline parallelism, activation checkpointing, mixed precision, optimizer state sharding (OSS), and auto-wrapping policies that reduce boilerplate in complex distributed setups. Its components are modular, so teams can adopt just the sharding optimizer or the pipeline engine without rewriting their training loop. ... -
16
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the... -
17
Img Optimizer Gradle Plugin
Gradle plugin for optimizing PNGs
...Because it is integrated into the build, it can process only changed images and skip redundant work, improving performance. Its configuration is minimal, making it easy to adopt in existing Android projects. For apps sensitive to download size or memory usage, this plugin offers a practical way to squeeze out extra gains in deployment efficiency. -
18
SimSiam
PyTorch implementation of SimSiam
SimSiam is a PyTorch implementation of “Exploring Simple Siamese Representation Learning” by Xinlei Chen and Kaiming He. The project introduces a minimalist approach to self-supervised learning that avoids negative pairs, momentum encoders, or large memory banks—key complexities of prior contrastive methods. SimSiam learns image representations by maximizing similarity between two augmented views of the same image through a Siamese neural network with a stop-gradient operation, preventing... -
19
Rdbtools
Parse Redis dump.rdb files, Analyze Memory, and Export Data to JSON
Rdbtools is a parser for Redis' dump.rdb files. The parser generates events similar to an XML sax parser and is very efficient memory-wise. Rdbtools is written in Python, though there are similar projects in other languages. Every run of RDB Tool requires to specify a command to indicate what should be done with the parsed RDB data. Valid commands are JSON, diff, justkeys, justkeyvals and protocol. The JSON command output is UTF-8 encoded JSON. By default, the callback try to parse RDB data using UTF-8 and escape non 'ASCII printable' characters with the \U notation, or non-UTF-8 parsable bytes with \x. ... -
20
JILRuntime/JewelScript
An object-oriented script language to embed in any application
A general purpose, object-oriented script language that compiles into code for a register based virtual machine. The language is quite similar to object-oriented high-level languages like Java and C#. The library is entirely self-sufficient and ANSI C compliant. It's main purpose is to be embedded in any application to allow automation of that application through scripting. An integrated C++ binding code generator allows you to create bindings for your application's classes in seconds.... -
21
fem2d
2D Finite Element Method Tools
Collection of programs developed to perform various engineering analyses on structures using the finite element technique. -
22
FyDB is a distributed in-memory no-SQL DB. It supports distributed deployment, and can integrate heterogeneous data sources. Data of FyDB is stroed in memory as key-value structure, and it is also persistent. Join this project: fuyuncat@gmail.com
-
23
DiffusionGemma
NVFP4 DiffusionGemma model for fast multimodal text generation
...The model supports a 256K-token context window, configurable thinking mode, native function calling, structured JSON output, and multilingual inference across 35+ languages. The NVFP4 quantization reduces weights and activations from 16-bit to 4-bit, lowering disk size and GPU memory needs for vLLM deployment.
- Previous
- You're on page 1
- Next