Skip to content

[feat] add H3 video config on H200 / [feat] 在 H200 上新增 H3 视频配置 - #4970

Open
edwingao28 wants to merge 3 commits into
mainfrom
feat/h3-video-h200
Open

edwingao28 wants to merge 3 commits into
mainfrom
feat/h3-video-h200

Conversation

@edwingao28

Copy link
Copy Markdown
Collaborator

Summary

H3 video results on H200 come from one engine, SGLang. This adds vLLM-Omni on the same H200 workload so the two can be compared, as #4874 did on B200: h3-bf16-h200-vllm-omni-video runs vLLM-Omni v0.32.0, pinned by its linux/amd64 digest, on 1, 2, 4 and 8 H200 GPUs with the spec and set the SGLang H200 key uses (h3-v2.yaml release-v1, C1). The bound plan hash equals SGLang's (a5c800f1…) on every point.

Changes:

Risks: the 1-GPU point runs without offload on 141 GB, as SGLang's does; the sweep is the first vLLM-Omni run on H200.

Delivery: needs the PR full sweep on H200 (4 points).

中文

概要

H200 上的 H3 视频结果目前只有 SGLang 一个引擎。本 PR 与 #4874 在 B200 上的做法相同,在同一 H200 负载上新增 vLLM-Omni 以便比较:h3-bf16-h200-vllm-omni-video 在 1、2、4、8 张 H200 上运行按 linux/amd64 digest 固定的 vLLM-Omni v0.32.0,spec 和 set 与 SGLang H200 key 相同(h3-v2.yaml release-v1,C1)。每个点位绑定的 plan hash 都与 SGLang 相同(a5c800f1…)。

改动:

风险: 与 SGLang 一样,单卡点位在 141 GB 上不使用 offload;本次 sweep 是 vLLM-Omni 在 H200 上的首次运行。

交付: 需要在 H200 上运行 PR full sweep(4 个点位)。

AI model disclosure

Prepared by an AI agent running in Perplexity Computer (orchestrator model: Claude Opus 5.5, as exposed by the runtime); the delegated agent that wrote the recipes, config and this description runs in the same session, and its exact model identifier could not be verified.

Created with Perplexity

Mirror the SGLang H200 H3 deployment (h3-v2.yaml release-v1, C1) with
vLLM-Omni on the same GPU counts, so both engines bind one plan hash.

Co-authored-by: Perplexity <noreply@perplexity.ai>
@github-actions

Copy link
Copy Markdown
Contributor

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。

Co-authored-by: Perplexity <noreply@perplexity.ai>
@edwingao28 edwingao28 added the full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended) label Nov 10, 2026

@claude claude Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Apart from the inline finding, I checked a few other things and found no problems. The changelog says the prompt-embedding cache is off, and that's accurate: the H200 recipe already sets OMNI_DIFFUSION_PROMPT_EMBED_CACHE: "0" in a line this PR doesn't touch. The revision bump to 5917730a… only affects this H200 recipe, which no config key used until now. The B200 recipe already uses that revision. Apart from gpu_type, the updated H200 recipe is now byte-identical to the B200 one, {gpus_per_node} substitution included.

Extended reasoning...

The PR adds one config key, h3-bf16-h200-vllm-omni-video, and makes the old, unused H200 vLLM-Omni recipe match the B200 recipe. It also adds a changelog block and updates three docs. No security-sensitive code is involved. CODEOWNERS covers nvidia-master.yaml, the h200-* recipe tree, MODELS.md and video-generation/, so owners need to review it. Per the repo's rules, the new benchmark also needs an accepted sweep before merge.

This review covers commit a30585e, which is no longer the latest commit on this pull request; later commits are not covered by it.

@github-actions

Copy link
Copy Markdown
Contributor

@edwingao28

Copy link
Copy Markdown
Collaborator Author

/use 42763517224

@github-actions

github-actions Bot commented Nov 12, 2026 •

Copy link
Copy Markdown
Contributor

@edwingao28 staged run 42763517224.

This run has no staged performance curves.

This run remains available across future /stage-results requests. Staging the same run ID again updates its staged data. Staging workflow

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended)

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

1 participant