Repository navigation
[VideoGenX] add MiniMax-H3 MI355X SGLang video sweep / [VideoGenX] 新增 MiniMax-H3 MI355X SGLang 视频扫描 - #4809
Conversation
|
Generally most InferenceX submissions don't need to add changes to the infx package. On the off chance they do, generally the diff is small. Please prompt your agent to clean your PR to keep your diff to only necessary & minimal changes too. We have an increased code quality bar for changes to the infx package. 中文大多数 InferenceX 提交通常不需要修改 infx 包。即使确实需要,改动通常也很小。请让你的 agent 清理 PR,使改动只包含必要且最小的内容。infx 包的改动有更高的代码质量要求。 |
|
Claude finished @edwingao28's task in 49s —— View job Review: no blocking issues foundI read the full diff against
Not verified here:
|
H200 1-GPU held its allocation 105 min in run 41992035811, past the 75-min limit. [skip-sweep]
# Conflicts: # inferencex-e2e/perf-changelog.yaml
[skip-sweep] # Conflicts: # inferencex-e2e/docs/MODELS.md # inferencex-e2e/docs/video-generation.md # inferencex-e2e/perf-changelog.yaml # video-generation/README.md # video-generation/README_zh.md # video-generation/evaluator/srt_selected.py # video-generation/tests/test_srt_selected.py
[skip-sweep]
[skip-sweep]
|
/use 42118905701 |
|
@edwingao28 staged run 42118905701. This run has no staged performance curves. This run remains available across future |
Summary
Add a MiniMax-H3 C1 video sweep on four MI355X GPUs with SGLang Ulysses4 on the
h3-v2.yamlworkload of the H100 and B200 rows. The image is the SGLang v0.5.23 ROCm 7.2.4 MI35x build. On ROCm the server names each GPU by its board serial, matching AMD power samples; NVIDIA keeps CUDA UUIDs.Testing: CPU checks pass; the matrix plans one MI355X point. No GPU run yet: a trusted
e2e-tests.ymldispatch follows once H3 weights are staged on the MI355X shared cache.Stacked on #2916.
AI model disclosure
PR checklist and change type
Type of Change
Checklist
python -m infx.matrix.changed --base origin/mainlists affected config keys, I have appended one new entry covering them to the physical end ofinferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entriesinferencex-e2e/perf-changelog.yamlentry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs):full-sweep-fail-fast(recommended),full-sweep-enabled, ornon-canary-full-sweep-enabled. Optional modifiersall-evals,evals-only, andagentx-fastrequire a primary label; the last two block reuse while applied.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
新增 MiniMax-H3 在 4 张 MI355X 上的 C1 视频扫描,使用 SGLang Ulysses4,工作负载与 H100、B200 两行相同,都是
h3-v2.yaml。镜像为 SGLang v0.5.23 的 ROCm 7.2.4 MI35x 版本。在 ROCm 上,服务端用板卡序列号标识每张 GPU,与 AMD 功耗采样的标识方式一致;NVIDIA 仍使用 CUDA UUID。测试: CPU 检查通过,矩阵规划出一个 MI355X 数据点。尚未跑 GPU:等 H3 权重放到 MI355X 共享缓存后,再用 trusted 模式手动触发
e2e-tests.yml。基于 #2916。
AI 模型:claude-opus-5-5,负责实现和 PR 文案。