- Ascend 910, Ascend 910 Pro B (Ascend-cann-kernels-910) unplanned yet
From a technical view, vllm-ascend support would be possible if the torch-npu is supported. Otherwise, we have to implement it by using custom ops. We are also welcome to join us to improve together.
You can get our containers at `Quay.io`, e.g., [<u>vllm-ascend</u>](https://quay.io/repository/ascend/vllm-ascend?tab=tags) and [<u>cann</u>](https://quay.io/repository/ascend/cann?tab=tags).
If you are in China, you can use `daocloud` to accelerate your downloading:
There are many channels that you can communicate with our community developers / users:
- Submit a GitHub [<u>issue</u>](https://github.com/vllm-project/vllm-ascend/issues?page=1).
- Join our [<u>weekly meeting</u>](https://docs.google.com/document/d/1hCSzRTMZhIB8vRq1_qOOjx4c9uYUxvdQvDsMV2JcSrw/edit?tab=t.0#heading=h.911qu8j8h35z) and share your ideas.
- Join our [<u>WeChat</u>](https://github.com/vllm-project/vllm-ascend/issues/227) group and ask your quenstions.
- Join our ascend channel in [<u>vLLM forums</u>](https://discuss.vllm.ai/c/hardware-support/vllm-ascend-support/6) and publish your topics.
### 5. What features does vllm-ascend V1 supports?
Find more details [<u>here</u>](https://github.com/vllm-project/vllm-ascend/issues/414).
Currently, only some models are improved. Such as `Qwen2 VL`, `Deepseek V3`. Others are not good enough. In the future, we will support graph mode and custom ops to improve the performance of vllm-ascend. And when the official release of vllm-ascend is released, you can install `mindie-turbo` with `vllm-ascend` to speed up the inference as well.
vllm-ascend is a plugin for vllm. Basically, the version of vllm-ascend is the same as the version of vllm. For example, if you use vllm 0.7.3, you should use vllm-ascend 0.7.3 as well. For main branch, we will make sure `vllm-ascend` and `vllm` are compatible by each commit.
Currently, only 1P1D is supported by vllm. For vllm-ascend, it'll be done by [this PR](https://github.com/vllm-project/vllm-ascend/pull/432). For NPND, vllm is not stable and fully supported yet. We will make it stable and supported by vllm-ascend in the future.
Currently, w8a8 quantization is already supported by vllm-ascend originally on v0.8.4rc2 or higher, If you're using vllm 0.7.3 version, w8a8 quantization is supporeted with the integration of vllm-ascend and mindie-turbo, please use `pip install vllm-ascend[mindie-turbo]`.
Please run DeepSeek with BF16 now, following the [Multi-Node DeepSeek inferencing tutorail](https://vllm-ascend.readthedocs.io/en/main/tutorials/multi_node.html)
If you're using vllm 0.7.3 version, this is a known progress bar display issue in VLLM, which has been resolved in [this PR](https://github.com/vllm-project/vllm/pull/12428), please cherry-pick it locally by yourself. Otherwise, please fill up an issue.
- **Functional test**: we added CI, includes portion of vllm's native unit tests and vllm-ascend's own unit tests，on vllm-ascend's test, we test basic functionality、popular models availability and [supported features](https://vllm-ascend.readthedocs.io/en/latest/user_guide/suppoted_features.html) via e2e test
- **Performance test**: we provide [benchmark](https://github.com/vllm-project/vllm-ascend/tree/main/benchmarks) tools for end-to-end performance benchmark which can easily to re-route locally, we'll publish a perf website like [vllm](https://simon-mo-workspace.observablehq.cloud/vllm-dashboard-v0/perf) does to show the performance test results for each pull request
- **Accuracy test**: we're working on adding accuracy test to CI as well.
Finnall, for each release, we'll publish the performance test and accuracy test report in the future.
### 14. How to fix the error "InvalidVersion" when using vllm-ascend?
It's usually because you have installed an dev/editable version of vLLM package. In this case, we provide the env variable `VLLM_VERSION` to let users specify the version of vLLM package to use. Please set the env variable `VLLM_VERSION` to the version of vLLM package you have installed. The format of `VLLM_VERSION` should be `X.Y.Z`.
OOM errors typically occur when the model exceeds the memory capacity of a single NPU. For general guidance, you can refer to [vLLM's OOM troubleshooting documentation](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#out-of-memory).
In scenarios where NPUs have limited HBM (High Bandwidth Memory) capacity, dynamic memory allocation/deallocation during inference can exacerbate memory fragmentation, leading to OOM. To address this:
- **Adjust `--gpu-memory-utilization`**: If unspecified, will use the default value of `0.9`. You can decrease this param to reserve more memory to reduce fragmentation risks. See more note in: [vLLM - Inference and Serving - Engine Arguments](https://docs.vllm.ai/en/latest/serving/engine_args.html#vllm.engine.arg_utils-_engine_args_parser-cacheconfig).
- **Configure `PYTORCH_NPU_ALLOC_CONF`**: Set this environment variable to optimize NPU memory management. For example, you can `export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` to enable virtual memory feature to mitigate memory fragmentation caused by frequent dynamic memory size adjustments during runtime, see more note in: [PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html).
