mirage-project/mirage

Health v2 · maintenance only

Adoption not part of the score

2452 stars · 242 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Mirage Persistent Kernel (MPK) is a compiler and runtime that transforms multi-GPU LLM inference into a single fused megakernel, reducing inference latency by 1.2x to 6.7x. It compiles Hugging Face models like Qwen3 into a persistent GPU kernel with minimal developer effort.

Use cases

• compile LLMs into a single megakernel for low-latency inference
• reduce multi-GPU LLM inference latency without manual kernel tuning
• fuse computation and communication across GPUs into one kernel launch
• profile and visualize GPU task execution timelines for LLM inference
• serve Hugging Face models like Qwen3 with a persistent kernel runtime

When to choose

• you need minimal inference latency for LLM serving on NVIDIA GPUs
• you want to avoid hand-writing fused CUDA kernels for multi-GPU inference
• you're comfortable building from source and working with a research-grade compiler

When to avoid

• you need a production-ready inference server with broad model support out of the box
• you don't have NVIDIA GPUs or multi-GPU setups
• you need pre-built wheels or stable APIs, which are still in progress

Facets

library · maturity active

compiler llm-inference gpu-computing machine-learning interpreter large-language-models gpu-computing compilers machine-learning performance python megakernel kernel-fusion multi-gpu inference-optimization cuda persistent-kernel huggingface gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mirage-project/mirage")