# microsoft/Tutel

Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

Repository: https://github.com/microsoft/Tutel
Canonical: https://ross.abutalabs.com/products/tutel
Language: C
License: MIT
License Family: permissive
Topics: pytorch, moe, mixture-of-experts, deepseek, llm
Last push: 2026-09-02T06:08:25+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 40, longevity 100
- inputs: {"age_days": 1853, "days_push": 0, "days_rel": 531, "gap_med": 27, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1016, forks 112 (observed 2026-09-03T02:15:14.996569+00:00)

## What it is
Tutel is Microsoft's optimized Mixture-of-Experts (MoE) library for efficient training and inference of large language models, featuring dynamic parallelism/sparsity switching and low-precision (FP8/NVFP4/MXFP4) inference for MoE models like DeepSeek, Kimi, GLM, Qwen3, and GPT-OSS. It runs on NVIDIA and AMD GPUs (A100, H100, MI300 series) and integrates with PyTorch.

## Use cases
- run mixture-of-experts LLM inference with FP8 or FP4 quantization
- train MoE models efficiently on multi-GPU clusters
- serve DeepSeek or Kimi models on AMD MI300X GPUs
- speed up MoE expert routing in PyTorch
- fit large MoE models into limited GPU memory with NVFP4
- benchmark MoE inference throughput against vLLM or SGLang

## When to choose
- you need optimized MoE training or inference on NVIDIA or AMD GPUs
- you want to run very large MoE models (DeepSeek, Kimi, GLM) with FP4/FP8 quantization on limited VRAM
- you need dynamic parallelism switching for MoE workloads in PyTorch

## When to avoid
- you need a general-purpose LLM serving stack with broad model support and tooling
- your models are dense (non-MoE) transformers
- you need a simple single-GPU inference solution without multi-GPU hardware

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, llm-training, machine-learning, gpu-computing
- domain: large-language-models, deep-learning, machine-learning, gpu-computing
- platform: python, cloud
- tags: mixture-of-experts, moe, pytorch, quantization, fp8, nvfp4, mxfp4, deepseek, distributed-training, inference-optimization, linux, gpu, docker

## Member repositories
- microsoft/Tutel (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:14.996569+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:11:33.989106+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Tutel (fetched 2026-09-03T02:15:14.996569+00:00, sha 0427742200e8)
- Data as of 2026-08-30T08:39:29.467469+00:00.