DeepSeek-R1-INT4-FlagOS-Iluvatar provides an all-in-one deployment solution, enabling execution of DeepSeek-R1-INT4 on Iluvatar GPUs. As the first-generation release for the ILUVATAR, this package delivers three key features:
Open-source inference execution code, preconfigured with all necessary software and hardware settings.
Pre-built Docker image for rapid deployment on ILUVATAR.
Consistency Validation:
Evaluation tests verifying consistency of results between the official and ours.
Technical Summary
Serving Engine
We use FlagScale as the serving engine to improve the portability of distributed inference.
FlagScale is an end-to-end framework for large models across multiple chips, maximizing computational resource efficiency while ensuring model effectiveness. It ensures both ease of use and high performance for users when deploying models across different chip architectures:
One-Click Service Deployment: FlagScale provides a unified and simple command execution mechanism, allowing users to fast deploy services seamlessly across various hardware platforms using the same command. This significantly reduces the entry barrier and enhances user experience.
Automated Deployment Optimization: FlagScale automatically optimizes distributed parallel strategies based on the computational capabilities of different AI chips, ensuring optimal resource allocation and efficient utilization, thereby improving overall deployment performance.
Automatic Operator Library Switching: Leveraging FlagScale's unified Runner mechanism and deep integration with FlagGems, users can seamlessly switch to the FlagGems operator library for inference by simply adding environment variables in the configuration file.
Triton Support
We validate the execution of DeepSeek-R1-INT4 model with a Triton-based operator library as a PyTorch alternative.
We use a variety of Triton-implemented operation kernels—approximately 70%—to run the DeepSeek-R1-INT4 model. These kernels come from two main sources:
Most Triton kernels are provided by FlagGems (https://github.com/FlagOpen/FlagGems). You can enable FlagGems kernels by setting the environment variable USE_FLAGGEMS. For more details, please refer to the "How to Run Locally" section.
Also included are Triton kernels from vLLM, including fused MoE.
Introduction
DeepSeek-R1-INT4-FlagOS-Iluvatar provides an all-in-one deployment solution, enabling execution of DeepSeek-R1-INT4 on Iluvatar GPUs. As the first-generation release for the ILUVATAR-BI150, this package delivers three key features:
Open-source inference execution code, preconfigured with all necessary software and hardware settings.
Pre-built Docker image for rapid deployment on ILUVATAR-BI150.
Consistency Validation:
Evaluation tests verifying consistency of results between the official and ours.
Technical Summary
Serving Engine
We use FlagScale as the serving engine to improve the portability of distributed inference.
FlagScale is an end-to-end framework for large models across multiple chips, maximizing computational resource efficiency while ensuring model effectiveness. It ensures both ease of use and high performance for users when deploying models across different chip architectures:
One-Click Service Deployment: FlagScale provides a unified and simple command execution mechanism, allowing users to fast deploy services seamlessly across various hardware platforms using the same command. This significantly reduces the entry barrier and enhances user experience.
Automated Deployment Optimization: FlagScale automatically optimizes distributed parallel strategies based on the computational capabilities of different AI chips, ensuring optimal resource allocation and efficient utilization, thereby improving overall deployment performance.
Automatic Operator Library Switching: Leveraging FlagScale's unified Runner mechanism and deep integration with FlagGems, users can seamlessly switch to the FlagGems operator library for inference by simply adding environment variables in the configuration file.
Triton Support
We validate the execution of DeepSeek-R1-INT4 model with a Triton-based operator library as a PyTorch alternative.
We use a variety of Triton-implemented operation kernels—approximately 70%—to run the DeepSeek-R1-INT4 model. These kernels come from two main sources:
Most Triton kernels are provided by FlagGems (https://github.com/FlagOpen/FlagGems). You can enable FlagGems kernels by setting the environment variable USE_FLAGGEMS. For more details, please refer to the "How to Run Locally" section.
Also included are Triton kernels from vLLM, including fused MoE.
Bundle Download
Requested by Iluvatar, the file of docker image and model files should be applied by email.
Usage
Cambricon
Basic Image
basic software environment that supports model running
services@iluvatar.comContact by email，please indicate the unit/contact person/contact information/equipment source/specific requirements
