Trending/LLM & models

LLM & models

sqliteai/warp

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from…

★ 2,525Week rank 235 · star gain starts at the next snapshot

View on GitHub

From the README

WARP — Weight-Aware Runtime and Paging (formerly WASTE) WARP is an embeddable inference engine written in C, with no third-party runtime dependencies. It keeps the model trunk in memory, streams selected experts directly from disk, and uses the remaining RAM as a bounded expert cache.

Setup prompt

Paste this into Cursor or Claude Code. It only includes install lines found in the README, and it asks the agent to review the code first.

Set up the GitHub repository sqliteai/warp (Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.).
Repository: https://github.com/sqliteai/warp

The README does not contain a clear install command. Read the README and follow the official install steps. Do not invent package names.
Review the code before running anything.

Buzz by window

Same mentions, three half-lives. This is not a star history. Star gain appears after a second daily snapshot.

  • Today0.00
  • Week0.00
  • Month0.01

Spotted on

Related

Report a problem or request removal