Categories / LLM Infrastructure

An inference engine for NVIDIA RTX card card family, built for a coding agent and its subagents, and a companion that listens, reads and draws: Qwen3.8 27B and 125B Flash-Next MoE, Qwen-Image-2.1, Qwen3-ASR on the CPU. OpenAI-compatible API and Playground in one binary.

Last push 17 hours ago

blackwellcoding-agentscudainference-enginellmllm-inferencelocal-llmmixture-of-expertsnvfp4openai-apiopenai-compatibleqwenqwen3rtx-5090rustself-hostedspeculative-decodingspeech-to-text

Created

Sep 2026

Total stars

67

Last 7 days

0

Last 30 days

0

Last 12 months

0

README badge

Rusty Stars badge for gpillon/ignis
[![Rusty Stars](https://rustystars.dev/badge/gpillon/ignis.svg)](https://rustystars.dev/gpillon/ignis)