87ebaef4e4
### What this PR does / why we need it? Based on the design of dual-batch overlap proposed by Deepseek team and also the implementation of fused moe in VLLM project, we implement the multi-stream(also known as dual-batch) overlap for deepseek+mla on Ascend NPU. We split the input batch of model into two microbatches and then overlap the comp/comm ops in attention and moe layers using two streams to improve the performance. Our approach can be easily extended when adding dispatch/combine communications for moe layer. Compared with the previously proposed [draft](https://github.com/vllm-project/vllm-ascend/pull/842), we use one stream for computation ops and the other for communication ops, separately. In out opinions, it is beneficial for arranging the order of executing different ops and thus avoiding the contention of computation/communication resources. ref: [overlap for llama](https://github.com/vllm-project/vllm/pull/15787/files) ref: [dbo in sglang](https://github.com/sgl-project/sglang/pull/4068/files#diff-b4937569fc71f6ad215181b633b2f89c7183a2b4ac39e41fc22635599a9be7de) ### Does this PR introduce _any_ user-facing change? Adding an env variable "VLLM_ENABLE_DBO". Users can enable dbo by setting "VLLM_ASCEND_ENABLE_DBO=1" See /examples/offline_dualbatch_overlap_npu.py for more info. ### How was this patch tested? This patch can be tested with vllm-0.9.0 using its online service with benchmark tests. We have decoupled the func of dbo from vllm and it should be able to run without any modification to the code of vllm(some modifications is better to implement in vllm though). Any advice/discussion is welcome. ### Performance Benchmark We have ran the benchmark_serving script of vllm to test the performance after using dual-batch overlap. `python -m vllm.entrypoints.openai.api_server \ --model=DeepSeek-R1-W8A8 \ --trust-remote-code \ --distributed-executor-backend=mp \ -tp=16 \ --port 8006 \ --max-num-seqs 390 \ --max-model-len 32768 \ --max-num-batched-tokens 65536 \ --block-size 128 \ --compilation_config 0 \ --gpu-memory-utilization 0.90 \ --disable-log-requests \ --additional-config '{"expert_tensor_parallel_size":1,"enable_inter_dp_scheduling":true,"init_torchair_graph_batch_sizes":true,"trace_recompiles":true,"ascend_scheduler_config":{},"enable_graph_mode":false}'` and run benchmark with the parameters of : `--dataset-name random --random-input-len 4096 --random-output-len 1 --num-prompts 200 --max-concurrency 8 --request-rate 5 --metric-percentiles 90` 1. test with the version using allgather+allreduce in Ascend 910B (tp16 ep16 + deepseek r1 w8a8) 2. test with the version using alltoall: prefill qps: 0.90 -> 1.01 Mean TTFT：8226->7432ms The overlap approach when using alltoall communication can be further optimized by overlapping micro-batch1's moe comp with micro-batch2's dispatch a2a comm --------- Signed-off-by: zhuohuan <zxdu1997@gmail.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.