Search Results for "wise memory optimizer"
Sort By:
Showing 10 open source projects for "wise memory optimizer"
View related business solutions-
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.
-
Paessler - Monitor Your Whole Network in MinutesWaiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.
-
1
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
MSA, or Memory Sparse Attention, is a research framework for scaling language-model memory to extremely long contexts. It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. -
2
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... -
3
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. ... -
4
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. ... -
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
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. -
6
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. -
7
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. ... -
8
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... -
9
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... -
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.
-
10
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. ...
- Previous
- You're on page 1
- Next
