e9ada685ec
[CI]Moe alltoall communication optimization The DeepSeek V3/R1 model has 256 routing experts. During parallel inference, if the load of an EP rank is high, the overall communication and computing time is slowed down, which becomes a weakness of parallel inference because the load is unevenly distributed. However, the data volume in the prefill phase is large, and the inter-card communication time consumption/calculation time consumption and the data volume are closely related to each other. Therefore, less non-linear precision loss can be used to obtain a near-linear performance improvement. During parallel inference, global synchronization occurs during communication. As a result, the card with low load completes the calculation first and waits for the card with the highest load to complete the calculation. Therefore, if the load is unbalanced, the card with high load slows down the overall time consumption. Significant performance gains can be achieved by discarding a small number of tokens, which is unacceptable in some precision-sensitive scenarios. However, similar to quantification, it is a solution that uses an acceptable precision loss in some scenarios for performance. In addition, a trade-off between performance and precision can be achieved by configuring a proportion of discarded tokens. Perform the test on A3. The batch size is 8 (B), the prompt length is 3.5K tokens (S), and the parallel configuration is as follows: AttnDP=2, AttnTP=8, MoeTP=1, and MoeEP=16. In this sence, we got a 10%-15% performance gain. Plus, the next version, we'll have an alltoallv moe. --------- Signed-off-by: weijinqian_v1 <weijinqian@huawei.com> Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
vLLM Ascend Plugin
| About Ascend | Documentation | #sig-ascend | Users Forum | Weekly Meeting |
English | 中文
Latest News 🔥
- [2025/03] We hosted the vLLM Beijing Meetup with vLLM team! Please find the meetup slides here.
- [2025/02] vLLM community officially created vllm-project/vllm-ascend repo for running vLLM seamlessly on the Ascend NPU.
- [2024/12] We are working with the vLLM community to support [RFC]: Hardware pluggable.
Overview
vLLM Ascend (vllm-ascend) is a community maintained hardware plugin for running vLLM seamlessly on the Ascend NPU.
It is the recommended approach for supporting the Ascend backend within the vLLM community. It adheres to the principles outlined in the [RFC]: Hardware pluggable, providing a hardware-pluggable interface that decouples the integration of the Ascend NPU with vLLM.
By using vLLM Ascend plugin, popular open-source models, including Transformer-like, Mixture-of-Expert, Embedding, Multi-modal LLMs can run seamlessly on the Ascend NPU.
Prerequisites
- Hardware: Atlas 800I A2 Inference series, Atlas A2 Training series
- OS: Linux
- Software:
- Python >= 3.9, < 3.12
- CANN >= 8.1.RC1
- PyTorch >= 2.5.1, torch-npu >= 2.5.1
- vLLM (the same version as vllm-ascend)
Getting Started
Please refer to QuickStart and Installation for more details.
Contributing
See CONTRIBUTING for more details, which is a step-by-step guide to help you set up development environment, build and test.
We welcome and value any contributions and collaborations:
- Please let us know if you encounter a bug by filing an issue
- Please use User forum for usage questions and help.
Branch
vllm-ascend has main branch and dev branch.
- main: main branch，corresponds to the vLLM main branch, and is continuously monitored for quality through Ascend CI.
- vX.Y.Z-dev: development branch, created with part of new releases of vLLM. For example,
v0.7.3-devis the dev branch for vLLMv0.7.3version.
Below is maintained branches:
| Branch | Status | Note |
|---|---|---|
| main | Maintained | CI commitment for vLLM main branch and vLLM 0.9.x branch |
| v0.7.1-dev | Unmaintained | Only doc fixed is allowed |
| v0.7.3-dev | Maintained | CI commitment for vLLM 0.7.3 version |
Please refer to Versioning policy for more details.
Weekly Meeting
- vLLM Ascend Weekly Meeting: https://tinyurl.com/vllm-ascend-meeting
- Wednesday, 15:00 - 16:00 (UTC+8, Convert to your timezone)
License
Apache License 2.0, as found in the LICENSE file.