Skip to content

Add DSV4 FP4 B200 Dynamo SGLang configuration / 新增 DSV4 FP4 B200 Dynamo SGLang 配置#2251

Open
RohitNagraj wants to merge 3 commits into
mainfrom
dsv4-fp4-b200-dynamo-sglang
Open

Add DSV4 FP4 B200 Dynamo SGLang configuration / 新增 DSV4 FP4 B200 Dynamo SGLang 配置#2251
RohitNagraj wants to merge 3 commits into
mainfrom
dsv4-fp4-b200-dynamo-sglang

Conversation

@RohitNagraj

@RohitNagraj RohitNagraj commented Jul 16, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Add a B200 multinode Dynamo SGLang configuration for DSV4 FP4.
  • Add checked-in srt-slurm recipes for the configured 8k/1k disaggregated topologies.
  • Configure the B200 launcher with the DSV4 FP4 model path and required preflight handling.

Validation

  • Generated all configured sweep combinations successfully.
  • Validated the changelog entry.
  • Validated launcher shell syntax and recipe/config consistency.

中文说明

  • 新增用于 DSV4 FP4 的 B200 多节点 Dynamo SGLang 配置。
  • 新增已检入的 srt-slurm recipe,覆盖配置中的 8k/1k 分离式拓扑。
  • 配置 B200 启动器,接入 DSV4 FP4 模型路径及所需的预检参数处理。

验证

  • 已成功生成全部配置扫描组合。
  • 已验证性能变更日志条目。
  • 已验证启动器 Shell 语法以及 recipe 与配置的一致性。

@github-actions

Copy link
Copy Markdown
Contributor

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

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. See GitHub's docs on re-running failed jobs


感谢你的贡献!请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md,然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人,你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板,包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have

如需进行 PR 验证,请为此 PR 添加 full-sweep-fail-fast 标签(强烈推荐)— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled

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。参见 GitHub 关于重新运行失败任务的文档

@RohitNagraj RohitNagraj changed the title Add DSV4 FP4 B200 Dynamo SGLang configuration Add DSV4 FP4 B200 Dynamo SGLang configuration / 新增 DSV4 FP4 B200 Dynamo SGLang 配置 Jul 16, 2026
Comment thread perf-changelog.yaml
Comment thread perf-changelog.yaml
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

1 participant