# Can Ascend officially draft a documentation on the vLLM-Ascend adaptation for graph mode?

**URL:** <https://discuss.vllm.ai/t/can-ascend-officially-draft-a-documentation-on-the-vllm-ascend-adaptation-for-graph-mode/162>\
**Category:** Ascend Support\
**Created:** [March 21, 2025, 5:31am UTC](https://discuss.vllm.ai/t/can-ascend-officially-draft-a-documentation-on-the-vllm-ascend-adaptation-for-graph-mode/162 "2025-03-21T05:31:59Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![Chuanyu](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/chuanyu/32/33_2.png) [@Chuanyu](https://discuss.vllm.ai/u/Chuanyu)\
**Post date:** [March 22, 2025, 6:22am UTC](https://discuss.vllm.ai/t/can-ascend-officially-draft-a-documentation-on-the-vllm-ascend-adaptation-for-graph-mode/162/5 "2025-03-22T06:22:03Z")

</div>

Basically: Graph mode provides two core acceleration capabilities, kernel fusion and framework overhead reduce benefits, all capabilities will be provided based on torch.compile.  
Regarding reduce-overhead , which is equivalent to cudagraph functionality, named aclgraph will be officially released by Q2 at the latest.  
Regarding automatic fusion, multiple teams are attempting different implementation approaches, and once mature, we will introduce and integrate them.  
Torchair, as the graph mode bridge between torch and ascend, will provide different user experiences in the future through various config\_mode options.  
If the automatic fusion capability based on inductor matures in the future, we will also consider directly providing inductor-npu backend.

---

_[View the full topic](https://discuss.vllm.ai/t/can-ascend-officially-draft-a-documentation-on-the-vllm-ascend-adaptation-for-graph-mode/162)._