Repository navigation
[VideoGenX] run matched Wan workloads on SGLang and vLLM-Omni - #3733
Closed
edwingao28 wants to merge 60 commits into
Closed
edwingao28 wants to merge 60 commits into
edwingao28 wants to merge 60 commits into
Conversation
移植既有 H3 视频流程到当前主线,保留独立资源生命周期和结果契约;对齐正式 changelog 解析、暂存功耗模块、AMD SMI 与封装脚本校验。
补回 H3 父 PR 已有的测试清理:删除仅回显 stub 输入的断言,保留 CLI 退出行为验证。
在当前主线移除 utils 兼容入口后,改用 infx 功耗模块与优先级 CLI,保留隔离暂存和 Python 3.10 兼容,并同步依赖路径及中英文说明。
将 feat/h3-cross-hardware 与当前 main 合并;保留 H3 changelog 条目并追加在 main 新增条目之后,维持 append-only 契约。 Co-authored-by: Wenyao Gao <edwingao28@users.noreply.github.com>
将 H3 工作流、暂存功耗打包与 AMD 辅助脚本对齐到 inferencex-e2e/ 布局;保留 staged 包内的 infx/ 导入契约与手动派发路径。 Co-authored-by: Wenyao Gao <edwingao28@users.noreply.github.com>
新增 Wan 视频服务与部署证据投影,保留 H3 行为。
Contributor
|
Thanks for the contribution!
中文感谢你的贡献!
|
edwingao28
force-pushed
the
feat/h3-cross-hardware
branch
6 times, most recently
from
October 17, 2026 04:31
ddc4127 to
f7c7f58
Compare
…aluator Carries the MiniMax-H3 serving harness from #2916 onto main. The evaluator gains srt-serve/srt-client/srt-finalize so a generic srt-slurm service runs the diffusion server, each concurrency publishes its own measurement window, and the dashboard bundle is assembled from the native power package. 中文:将 #2916 的 MiniMax-H3 serving harness 迁移到 main。evaluator 新增 srt-serve/srt-client/srt-finalize:由 srt-slurm generic service 启动 diffusion server,每个并发度发布自己的测量窗口,并基于原生功耗包组装仪表板产物。
Adds the video-generation scenario to the vendor master configs and routes it to a new srt-video launch path: the recipe binds a custom benchmark plus the h3-server service, the job mounts the H3 package and HF cache, and infx.results.video validates every concurrency against the native power package with per-clip energy before the bundle is built. 中文:在厂商 master 配置中加入 video-generation scenario,并路由到新的 srt-video 启动路径:recipe 绑定 custom benchmark 与 h3-server service,作业挂载 H3 package 与 HF cache,infx.results.video 按并发度用原生功耗包校验并以每个 clip 归一化能耗,然后再组装产物。
edwingao28
force-pushed
the
feat/h3-cross-hardware
branch
from
October 17, 2026 04:42
f7c7f58 to
068d64f
Compare
e2e-tests.yml plans video-generation rows into a test-sweep-video job, the benchmark template passes the H3 spec and concurrency list to the launcher and uploads the h3-results bundle, and the standalone H3 workflows use the harness's check_env.sh. One perf-changelog entry covers the four H3 keys. 中文:e2e-tests.yml 将 video-generation 行规划到 test-sweep-video 作业,benchmark 模板向 launcher 传递 H3 spec 与并发度列表并上传 h3-results 产物,独立的 H3 workflow 改用 harness 的 check_env.sh。perf-changelog 新增一条覆盖四个 H3 键。
edwingao28
force-pushed
the
feat/h3-cross-hardware
branch
from
October 17, 2026 04:45
068d64f to
0cb4c84
Compare
# Conflicts: # experimental/video-generation/tests/test_srt_selected.py
edwingao28
changed the base branch from
feat/h3-cross-hardware
to
feat/videogenx-h3-vllm-omni
October 18, 2026 09:23
Base automatically changed from
feat/videogenx-h3-vllm-omni
to
feat/h3-cross-hardware
October 29, 2026 12:19
edwingao28
force-pushed
the
feat/h3-cross-hardware
branch
from
October 29, 2026 20:11
2c603bb to
5e2556d
Compare
edwingao28
force-pushed
the
feat/h3-cross-hardware
branch
11 times, most recently
from
November 3, 2026 09:53
6abe3b6 to
a6db760
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Run Wan2.2 on SGLang and vLLM-Omni through native sweeps with a shared 20-clip workload, immutable plans, and sealed failure evidence.
4475151c.Blocker: Depends on #4243. Native H200 GPU qualification remains unverified.
Related Issue
#2916, #4243, #4246.
Type of Change and Checklist
Type of Change
Checklist
inferencex-e2e/perf-changelog.yamland have not edited historical entriesOWNER/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 sweep label will no longer automatically kick off new sweeps. Remove and re-add the label to force one.