FlexGen is a high-throughput generation engine for running large language models with limited GPU memory. FlexGen allows high-throughput generation by IO-efficient offloading, compression and large effective batch sizes.
In recent years, large language models (LLMs) have shown great performance across a wide range of tasks. Increasingly, LLMs have been applied not only to interactive applications (such as chat), but also to many "back-of-house" tasks. These tasks include benchmarking, information extraction, data wrangling, and form processing.
One key characteristic of these applications is that they are throughput-oriented: they require running LLM inferences over millions of tokens in batches, e.g., all the private documents in a company's corpus, or all the tasks in the HELM benchmark. These workloads are less sensitive to latency - the user starts up a job and lets it run overnight - but increasing throughput is critical for reducing costs. Thoughput is a measure of tokens processed per second over the job's entire runtime (which can be hours). Throughput-oriented workloads provide opportunities to trading off latency for higher throughput, which makes it easier to take advantage of low-cost commodity GPUs.
The goal of FlexGen is to create a high-throughput system to enable new and exciting applications of foundation models to throughput-oriented tasks on low-cost hardware, such as a single commodity GPU instead of expensive systems. Here are some examples of high-throughput workloads that we can run on a single commodity GPU with FlexGen:
- Benchmarking: Running a subset of HELM benchmark.
- Data wrangling: Running data wrangling.
❌ Limitation. As an offloading-based system running on weak GPUs, FlexGen also has its limitations. FlexGen can be significantly slower than the case when you have enough powerful GPUs to hold the whole model, especially for small-batch cases. FlexGen is mostly optimized for throughput-oriented batch processing settings (e.g., classifying or extracting information from many documents in batches), on single GPUs.
This project was made possible thanks to a collaboration with
Requirements:
- PyTorch >= 1.12 (Help)
pip install flexgen
git clone https://github.com/FMInference/FlexGen.git
cd FlexGen
pip install -e .
FlexGen can be integrated into HELM, a language model benchmark framework, as its execution backend. You can use the commands below to run a Massive Multitask Language Understanding (MMLU) scenario with a single T4 (16GB) GPU and 200GB of DRAM.
python3 -m flexgen.apps.helm_run --description mmlu:model=text,subject=abstract_algebra,data_augmentation=canonical --pad-to-seq-len 512 --model facebook/opt-30b --percent 20 80 0 100 0 100 --gpu-batch-size 48 --num-gpu-batches 3 --max-eval-instance 100
See example
The corresponding effective batch sizes are in parentheses. Please see here for more details.
| System | OPT-6.7B | OPT-30B | OPT-175B |
|---|---|---|---|
| Hugging Face Accelerate | 25.12 (2 on GPU) | 0.62 (8 on CPU) | 0.01 (2 on disk) |
| DeepSpeed ZeRO-Inference | 9.28 (16 on CPU) | 0.60 (4 on CPU) | 0.01 (1 on disk) |
| Petals* | - | - | 0.05 |
| FlexGen | 25.26 (2 on GPU) | 7.32 (144 on CPU) | 0.69 (256 on disk) |
| FlexGen with Compression | 29.12 (72 on GPU) | 8.38 (512 on CPU) | 1.12 (144 on CPU) |
- Hardware: an NVIDIA T4 (16GB) instance on GCP with 208GB of DRAM and 1.5TB of SSD.
- Workload: input sequence length = 512, output sequence length = 32. The batch size is tuned to a large value that maximizes the generation throughput for each system.
- Metric: generation throughput (token/s) = number of the generated tokens / (time for processing prompts + time for generation).
How to reproduce.
We plan to work on the following features.
- Optimize the performance for multiple GPUs on the same machine
- Support more models (BLOOM, CodeGen, GLM)
- Release the cost model and policy optimizer