Search Results for "disk"

...Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. The architecture distributes computation and memory usage across the GPU, CPU, and disk in order to maximize the number of tokens processed during inference. This design allows organizations to deploy powerful language models for high-volume tasks without the infrastructure costs typically associated with large-scale AI systems. The project is particularly useful for workloads that prioritize throughput over latency, including benchmarking experiments and large corpus analysis.

Paperless-ngx is a community-supported open-source document management system that transforms your physical documents into a searchable online archive so you can keep, well, less paper.

The challenge is to run Stable Diffusion 1.5, which includes a large transformer model with almost 1 billion parameters, on a Raspberry Pi Zero 2, which is a microcomputer with 512MB of RAM, without adding more swap space and without offloading intermediate results on disk. The recommended minimum RAM/VRAM for Stable Diffusion 1.5 is typically 8GB. Generally, major machine learning frameworks and libraries are focused on minimizing inference latency and/or maximizing throughput, all of which at the cost of RAM usage. So I decided to write a super small and hackable inference library specifically focused on minimizing memory consumption: OnnxStream. ...

Pwnagotchi is an A2C-based “AI” powered by bettercap and running on a Raspberry Pi Zero W that learns from its surrounding WiFi environment in order to maximize the crackable WPA key material it captures (either through passive sniffing or by performing deauthentication and association attacks). This material is collected on disk as PCAP files containing any form of handshake supported by hashcat, including full and half WPA handshakes as well as PMKIDs. Instead of merely playing Super Mario or Atari games like most reinforcement learning based “AI” (yawn), Pwnagotchi tunes its own parameters over time to get better at pwning WiFi things in the real world environments you expose it to. ...

...Single order book configuration is capable to process 5M operations per second on 10-years old hardware (Intel® Xeon® X5690) with moderate latency degradation. HFT optimized. Priority is a limit-order-move operation mean latency (currently ~0.5µs). Cancel operation takes ~0.7µs, placing new order ~1.0µs. Disk journaling and journal replay support, state snapshots (serialization) and restore operations, LZ4 compression. Lock-free and contention-free order matching and risk control algorithms. Matching engine and risk control operations are atomic and deterministic.

Give an input CSV file and a target field you want to predict to automl-gs, and get a trained high-performing machine learning or deep learning model plus native Python code pipelines allowing you to integrate that model into any prediction workflow. No black box: you can see exactly how the data is processed, and how the model is constructed, and you can make tweaks as necessary. automl-gs is an AutoML tool which, unlike Microsoft's NNI, Uber's Ludwig, and TPOT, offers a zero code/model...

In data classification, there are no particular classifiers that perform consistently in every case. This is even worst in case of both the high dimensional and class-imbalanced datasets. To overcome the limitations of class-imbalanced data, we split the dataset using a random sub-sampling to balance them. Then, we apply the (alpha,beta)-k feature set method to select a better subset of features and combine their outputs to get a consolidated feature set for classifier training. To...