R_REDDYX.XYZ
AIC++★ 298⑂ 41 forksApache-2.0

Wallawalla47/Infernix

Infernix GPU Inference

C++/CUDA single-GPU inference engine for Qwen3.8 models, including Qwen3.8-Flash-Next with offloaded experts, optimized for RTX 5090; derived from NInfer.

// KEY FEATURES

  • Loads Qwen3.8 and Qwen3.8‑Flash‑Next models, offloading experts to GPU memory.
  • Executes single‑GPU inference on RTX 5090 using custom CUDA kernels.
  • Delivers low‑latency, high‑throughput chat completions for Qwen3.8‑style prompts.
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

HIVEMIND – UNIFIED BRAIN FOR AGENTS★ 298DAISO-MCP: KOREAN STORE SEARCH★ 298flashtype - MARKDOWN EDITOR FOR CODE★ 298QKNOW: AI Agent for Business★ 298RUSSIAN TEXT FOR AI AGENTS★ 298ALL SKILLS FOR AI AGENTS★ 298

← FULL CATALOG

Wallawalla47/Infernix — Infernix GPU Inference | REDDYX AI