MoE-Infinity is a cost-effective, fast, and easy-to-use library for Mixture-of-Experts (MoE) inference.

MoE-Infinity is cost-effective yet fast:

• Offloading MoE's experts to host memory, allowing memory-constrained GPUs to serve MoE models.
• Minimizing the expert offloading overheads through several novel techniques: expert activation tracing, activation-aware expert prefetching, and activation-aware expert caching.
• Supporting LLM acceleration techniques (such as FlashAttention).
• Supporting multi-GPU environments with numeorous OS-level performance optimizations.
• Achieving SOTA latency performance when serving MoEs in a resource-constrained GPU environment (in comparison with vLLM, HuggingFace Accelerate, DeepSpeed, Mixtral-Offloading, and Ollama/LLama.cpp).

MoE-Infinity is easy-to-use:

• HuggingFace model compatible, and HuggingFace programmer friendly.
• Supporting all available MoE checkpoints (including Deepseek-V2, Google Switch Transformers, Meta NLLB-MoE, and Mixtral).

Note that: The open-sourced MoE-Infinity has been redesigned for making it HuggingFace-users friendly. This version is different from the version reported in the paper, which takes extreme performance as the top priority. As a result, distributed inference is currently not supported in this open-sourced version.

• Performance
• Installation
  • Prerequisites
  • Install from conda environment
  • Install from PyPI
  • Install from Source
  • Enable FlashAttention (Optional)
• Usage and Examples
  • Sample Code of Huggingface LLM Inference
  • Running Inference
• Release Plan
• Citation

Single GPU A5000 (24GB Memory), per-token-latency (seconds) for generation with a mixed dataset that includes LongBench, GSM8K, FLAN, BIG-Bench and MMLU datasets. Lower per-token-latency is preferable.

We recommend installing MoE-Infinity in a virtual environment. To install MoE-Infinity, you can either install it from PyPI or build it from source.

conda create -n moe-infinity python=3.9
conda activate moe-infinity
# install from either PyPI or Source will trigger requirements.txt automatically

# install stable release
pip install moe-infinity
# install nightly release
pip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ moe-infinity

git clone https://github.com/EfficientMoE/MoE-Infinity.git
cd MoE-Infinity
pip install -e .
conda install -c conda-forge libstdcxx-ng=12 # assume using conda, otherwise install libstdcxx-ng=12 using your package manager or gcc=12

Install FlashAttention (>=2.5.2) for faster inference with the following command.

FLASH_ATTENTION_FORCE_BUILD=TRUE pip install flash-attn

Post-installation, MoE-Infinity will automatically integrate with FlashAttention to enhance performance.

We provide a simple API for diverse setups, including single GPU, multiple GPUs, and multiple nodes. The following examples show how to use MoE-Infinity to run generation on a Huggingface LLM model.

• The offload_path must be unique for each MoE model. Reusing the same offload_path for different MoE models will result in unexpected behavior.

import torch
import os
from transformers import AutoTokenizer
from moe_infinity import MoE
user_home = os.path.expanduser('~')
checkpoint = "deepseek-ai/DeepSeek-V2-Lite-Chat"
tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote=True)
config = {
 "offload_path": os.path.join(user_home, "moe-infinity"),
 "device_memory_ratio": 0.75, # 75% of the device memory is used for caching, change the value according to your device memory size on OOM
}
model = MoE(checkpoint, config)
input_text = "translate English to German: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda:0")
output_ids = model.generate(input_ids)
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output_text)

This command runs the script on selected GPUs.

CUDA_VISIBLE_DEVICES=0,1 python script.py

We provide a simple example to run inference on a Huggingface LLM model. The script will download the model checkpoint and run inference on the specified input text. The output will be printed to the console.

CUDA_VISIBLE_DEVICES=0 python examples/interface_example.py --model_name_or_path "deepseek-ai/DeepSeek-V2-Lite-Chat" --offload_dir <your local path on SSD>

Start the OpenAI-compatible server locally

python -m moe_infinity.entrypoints.openai.api_server --model deepseek-ai/DeepSeek-V2-Lite-Chat --offload-dir ./offload_dir

Query the model via /v1/components/. (We currently only support the required fields, i.e., "model" and "prompt").

curl http://localhost:8000/v1/completions \
 -H "Content-Type: application/json" \
 -d '{
 "model": "deepseek-ai/DeepSeek-V2-Lite-Chat",
 "prompt": "Hello, my name is"
 }'

You can also use openai python package to query the model.

pip install openai
python tests/test_oai_completions.py

Query the model via /v1/chat/completions. (We currently only support the required fields, i.e., "model" and "messages").

curl http://localhost:8000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -d '{
 "model": "deepseek-ai/DeepSeek-V2-Lite-Chat",
 "messages": [
 {"role": "system", "content": "You are a helpful assistant."},
 {"role": "user", "content": "Tell me a joke"}
 ]
 }'

You can also use openai python package to query the model.

pip install openai
python tests/test_oai_chat_completions.py

We plan to release two functions in the following months:

• We currently support PyTorch as the default inference engine, and we are in the process of supporting vLLM as another inference runtime, which includes the support of KV cache offloading.
• Supporting expert parallelism for distributed MoE inference.
• More (We welcome contributors to join us!)

If you use MoE-Inifity for your research, please cite our paper:

@misc{moe-infinity,
 author = {Leyang Xue and
 Yao Fu and
 Zhan Lu and
 Luo Mai and
 Mahesh Marina},
 title = {MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache},
 archivePrefix= {arXiv},
 eprint = {2401.14361},
 year = {2024}
}