Multi node ascend

[jinminxi104]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[Copilot]

Pull request overview

This PR updates LMDeploy’s PyTorch Ray-based execution path to better support Ascend (NPU) multi-node / multi-worker setups by ensuring key Ascend/HCCL-related environment variables propagate to Ray workers and by revising Ascend worker device assignment logic.

Changes:

• Capture additional Ascend/HCCL-related environment variables in lmdeploy.pytorch.envs so they can be forwarded into Ray worker runtime_env.
• Ensure non-GPU Ray workers are created with an explicit runtime_env, aligning behavior with the GPU path.
• Rework Ascend distributed initialization to support cross-node placement groups without relying on an Ascend rank-table JSON mapping.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
lmdeploy/pytorch/envs.py	Captures additional HCCL / Ascend env vars for forwarding into Ray worker runtime environments.
lmdeploy/pytorch/engine/executor/ray_executor.py	Passes runtime_env for non-GPU Ray workers and revises Ascend worker device assignment logic for multi-node placement groups.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.