[GH-ISSUE #4405] [Feature Request]: NPU wheels for pre-release versions #1109

New issue

Open

opened 2026-10-29 21:22:58 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-29 21:22:58 +00:00

Owner

Originally created by @zouyida2052 on GitHub (Sep 30, 2026).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/4405

I'm trying to use v0.3.14-rc1 with vLLM on Ascend, but couldn't find a mooncake-transfer-engine-npu wheel in the release assets. v0.3.13.post1 and earlier releases have them.

It looks like release-npu.yaml skips tags containing - because of !contains(github.ref_name, '-'), introduced in #2212. The rc1 NPU workflow run shows both jobs skipped, and the separate pre-release workflow only builds CUDA, CUDA 13, and non-CUDA wheels.

Could we include NPU wheels for pre-release tags like v0.3.14-rc1 as well? Having them on the GitHub Release page would be enough for us to test these versions without building from source. It would also help if the missing rc1 wheels could be uploaded.

Originally created by @zouyida2052 on GitHub (Sep 30, 2026). Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/4405 I'm trying to use `v0.3.14-rc1` with vLLM on Ascend, but couldn't find a `mooncake-transfer-engine-npu` wheel in the release assets. `v0.3.13.post1` and earlier releases have them. It looks like `release-npu.yaml` skips tags containing `-` because of `!contains(github.ref_name, '-')`, introduced in #2212. The [rc1 NPU workflow run](https://github.com/kvcache-ai/Mooncake/actions/runs/34108669990) shows both jobs skipped, and the separate pre-release workflow only builds CUDA, CUDA 13, and non-CUDA wheels. Could we include NPU wheels for pre-release tags like `v0.3.14-rc1` as well? Having them on the GitHub Release page would be enough for us to test these versions without building from source. It would also help if the missing rc1 wheels could be uploaded.

bsakaguchi commented

2026-10-29 21:22:59 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Sep 30, 2026):

Thanks for opening this issue, @zouyida2052!

Field	Value
Issue	#4405
GitHub user ID	`208782633`
Reporter	@zouyida2052

A maintainer will triage this when possible. To help us respond faster, please include:

Mooncake version or commit SHA
Environment (OS, CUDA/driver, RDMA stack if relevant)
Steps to reproduce and expected vs. actual behavior

Useful links: Documentation · Contributing guide

This message was posted automatically by the issue bot.

@github-actions[bot] commented on GitHub (Sep 30, 2026): Thanks for opening this issue, @zouyida2052! | Field | Value | |-------|-------| | **Issue** | #4405 | | **GitHub user ID** | `208782633` | | **Reporter** | @zouyida2052 | A maintainer will triage this when possible. To help us respond faster, please include: - Mooncake version or commit SHA - Environment (OS, CUDA/driver, RDMA stack if relevant) - Steps to reproduce and expected vs. actual behavior Useful links: [Documentation](https://kvcache-ai.github.io/Mooncake/) · [Contributing guide](https://github.com/kvcache-ai/Mooncake/blob/main/CONTRIBUTING.md) > This message was posted automatically by the issue bot.

bsakaguchi referenced this issue

2026-10-29 21:32:09 +00:00

[PR #1109] [CLOSED] add test py #2017