[Fangzhou-Ai]

Update DeepSeek-V4-Pro-0813 AgentX on MI355X from nightly-e9757321527ca1ecd514c07c1418dd2c53da3d19 to vllm/vllm-openai-rocm:nightly-e4a5b5537344b103ed10de7764378ef09604ef3d, the latest nightly published on October 25, and enable --monokernel for the nine pure-TP8 points.

Explicitly disable monokernel for the three data-parallel variants: the pinned upstream implementation requires TP8 without data or expert parallelism and rejects unsupported deployments at startup. Append one performance changelog entry covering the affected config. GPU serving behavior and performance remain unverified.

Upstream references: nightly image, Pro monokernel deployment requirements.

AI model disclosure

• Model/version: The exact model identifier could not be verified from the runtime.
• Role: Codex prepared the image update, recipe changes, changelog entry, and PR. No delegated agents contributed.

PR checklist and change type

Type of Change

• Bug fix
• New feature
• Configuration change
• Documentation update
• Other (please describe)

Checklist

• I have completed the AI model disclosure and kept it current
• I have tested my changes locally
• I have updated documentation if necessary
• If python -m infx.matrix.changed --base origin/main lists affected config keys, I have appended one new entry covering them to the physical end of inferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entries
• If this PR appends an inferencex-e2e/perf-changelog.yaml entry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs): full-sweep-fail-fast (recommended), full-sweep-enabled, or non-canary-full-sweep-enabled. Optional modifiers all-evals, evals-only, and agentx-fast require a primary label; the last two block reuse while applied.
• Before merging via reuse, an authorized maintainer (OWNER/MEMBER/COLLABORATOR) has commented /use <run_id> (or the legacy /reuse-sweep-run) on this PR. Do this only once there is a final full sweep that is all green with evals passing, since after this comment the primary sweep label will no longer automatically kick off new sweeps. Remove and re-add the primary sweep label to force a new sweep.

中文

将 MI355X 上 DeepSeek-V4-Pro-0813 AgentX 的镜像从 nightly-e9757321527ca1ecd514c07c1418dd2c53da3d19 更新为 10 月 25 日发布的最新 nightly：vllm/vllm-openai-rocm:nightly-e4a5b5537344b103ed10de7764378ef09604ef3d，并为九个纯 TP8 测试点启用 --monokernel。

三个 data-parallel 变体显式禁用 monokernel，因为该版本的上游实现要求 TP8 且不使用 data 或 expert parallelism，否则会在启动时报错。追加一条性能变更记录，覆盖受影响的配置。GPU 上的实际运行行为和性能尚未验证。上游依据见上方链接。

改动类型：配置变更。由 Codex 完成镜像更新、recipe 修改、性能变更记录和 PR；运行环境未提供可核实的精确模型标识，未使用委派 agent。合并前仍需获得包含 evals 的完整绿色 sweep，并由获授权的维护者提交 /use <run_id>。

[github-actions]

Thanks for the contribution!

• Review: If this PR changes files owned by someone other than a repository admin or @SemiAnalysisAI/core, ask one eligible CODEOWNER to complete the latest PR_REVIEW_CHECKLIST.md before contacting a core maintainer on Slack. Follow the template exactly, including As a PR reviewer and CODEOWNER, I have reviewed this and have, so sign-off verification triggers.
• PR verification: Sweeps run only when the PR appends an inferencex-e2e/perf-changelog.yaml entry and carries exactly one primary label: full-sweep-fail-fast (strongly recommended; canary plus per-matrix fail-fast), full-sweep-enabled (canary; matrix jobs continue after a failure), or non-canary-full-sweep-enabled (no canary or fail-fast). The modifiers all-evals, evals-only, and agentx-fast require a primary label. On fork PRs, a maintainer applies the label. See sweep labels and reuse.
• After merging: PR authors must ensure all GitHub Actions jobs pass. Transient failures often pass on rerun; see how to rerun failed jobs.

中文

感谢你的贡献！

• **审阅：**如果 PR 修改的文件归属于仓库管理员及 @SemiAnalysisAI/core 之外的 CODEOWNER，请先联系一位有资格的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，再通过 Slack 联系核心维护者。必须严格遵循模板，并保留 As a PR reviewer and CODEOWNER, I have reviewed this and have，才能触发签核验证。
• **PR 验证：**只有当 PR 在 inferencex-e2e/perf-changelog.yaml 末尾追加了条目，并且恰好带有一个主标签时，才会运行扫描：full-sweep-fail-fast（强烈推荐；canary 加逐矩阵 fail-fast）、full-sweep-enabled（有 canary；矩阵任务在失败后继续运行）或 non-canary-full-sweep-enabled（无 canary，也无 fail-fast）。修饰标签 all-evals、evals-only 和 agentx-fast 必须与主标签一起使用。fork PR 的标签由维护者添加。参见扫描标签与复用。
• **合并后：**PR 作者必须确保所有 GitHub Actions 任务通过。临时性失败通常可以通过重新运行恢复；参见重新运行失败任务的说明。

[claude]

Code review found no issues

No high-confidence issues detected in this change.

This review covers commit 3ab4fdc, which is no longer the latest commit on this pull request; later commits are not covered by it.

[github-actions]

View unofficial run (performance): https://inferencex.semianalysis.com/inference?unofficialRun=40260921924

View unofficial run (accuracy): https://inferencex.semianalysis.com/evaluation?unofficialRun=40260921924

[chunfangamd]

[chunfangamd]

/reuse-sweep-run 40260921924