This is the Linux app named WASTE whose latest release can be downloaded as v0.6.8sourcecode.zip. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named WASTE with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS:
WASTE
DESCRIPTION:
WASTE is an embeddable C inference engine for running extremely large mixture-of-experts models when the weights exceed available RAM. It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has no third-party runtime dependency on its CPU inference path and exposes both a CLI and C library. An optional server provides an OpenAI-compatible chat API with streaming, tools, structured output, and image support. Validation compares layers, logits, vision output, and prompt rendering against reference implementations.
Features
- NVMe-streamed mixture-of-experts inference
- Full Kimi K3 model support
- Bounded expert caching and lookahead routing
- Dependency-free C CPU inference path
- CLI, embeddable library, and HTTP server
- Multimodal text and image inference
Programming Language
C
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/waste.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.