[AMD] DeepSeek-V4 FP4 MI355X vLLM STP: bump image to latest nightly / DeepSeek-V4 FP4 MI355X vLLM STP：升级镜像至最新 nightly#1980
Conversation
Update dsv4-fp4-mi355x-vllm from vllm/vllm-openai-rocm:v0.22.0 to the latest nightly (nightly-09663abde0f50944a8d5ea30120666024b503faa).
Fangzhou-Ai
requested review from
1am9trash,
billishyahao,
chunfangamd,
seungrokj and
yctseng0211
as code owners
|
Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you
PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers. If additional help is needed, PR authors can reach out to core maintainers over Slack. 感谢你的贡献！对于 vLLM 与 SGLang，请确保你的 recipe 与官方 vLLM recipes 和/或 SGLang cookbook 保持一致 如果不一致，请先创建一个 PR，之后我们才能将你的单节点 PR 合并到 master 分支。让我们确保文档保持一流水准，使整个 ML 社区都能从你的辛勤工作中受益！谢谢
PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。如果选择重新运行失败的任务，PR 作者有责任确保其最终通过。参见 GitHub 关于重新运行失败任务的文档：https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow 一般而言，PR 作者应先向相应公司的 CODEOWNERS 请求审阅并获得 PR 批准，然后再请求核心维护者审阅。 如需更多帮助，PR 作者可通过 Slack 联系核心维护者。 |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=28591706847 |
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=28593351944 |
functionstackx
changed the title
|
/reuse-sweep-run |
# Conflicts: # perf-changelog.yaml
2 participants
Summary
Bumps the DeepSeek-V4-Pro FP4 MI355X single-node vLLM STP recipe (
dsv4-fp4-mi355x-vllm) image to the latestvllm/vllm-openai-rocmnightly.vllm/vllm-openai-rocm:v0.22.0vllm/vllm-openai-rocm:nightly-09663abde0f50944a8d5ea30120666024b503faa(latest nightly, 2026-07-02)Only the
.github/configs/amd-master.yamlimage pin and aperf-changelog.yamlentry change; the search space (TP8, conc 4-512, 1k1k + 8k1k) is unchanged. The MTP variant (dsv4-fp4-mi355x-vllm-mtp) is intentionally left onv0.22.0in this PR.AI assistance (Claude) was used to prepare this change.
Made with Cursor
中文说明
将 DeepSeek-V4-Pro FP4 MI355X 单节点 vLLM STP 配置的镜像从
v0.22.0升级至最新 nightly（2026-07-02）。仅变更amd-master.yaml中的镜像标签和perf-changelog.yaml条目，搜索空间（TP8, 并发 4-512, 1k1k + 8k1k）不变。MTP 变体在本 PR 中暂不升级。