#gpu

该仓库未发布描述。

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

An easy tool to monitor the performance of your R3F application.

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

该仓库未发布描述。

Spin up secure, throwaway multi-node cloud test clusters — CPU or GPU — for distributed C++/IPC software. One command up, nothing left behind.

Production-oriented browser CAD viewer for DWG, DXF, DWF, DWFx and XPS with LibreDWG WASM, WebGL/Canvas rendering, external SHX references and native DWF support.

A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.

📊 A simple command-line utility for querying and monitoring GPU status