R_REDDYX.XYZ
AIRust★ 240⑂ 40 forksApache-2.0

pie-project/pie

PIE — MODEL SERVING ON RUST

Programmable engine for high-performance LLM and diffusion model serving. Written in Rust, supports batching, KV caching, and dynamic adapter loading.

// KEY FEATURES

  • Serves LLM and diffusion models via unified API
  • Request batching and KV-cache for faster inference
  • Hot-loading LoRA adapters without restart
  • Written in Rust, delivers low latency and high throughput
#diffusion-model#inference#inference-engine#llm-inference#llms#machine-learning#mlsystem#multimodal
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Inference Engine for Cybersecurity★ 240YourMemory - AI Memory with Forgetting★ 240QVAC Local AI SDK★ 240AGENT-PULSE AI TRENDS REAL TIME★ 240CLAUDE CODE GPT-5 CODING PROXY★ 240MAUI LABS: NEW TOOLS★ 240

← FULL CATALOG

pie-project/pie — Pie — Model Serving ON Rust | REDDYX AI