[AMD] Refresh DeepSeek-R1 MI355X SGLang image / [AMD] 更新 DeepSeek-R1 MI355X SGLang 镜像 - #2691
[AMD] Refresh DeepSeek-R1 MI355X SGLang image / [AMD] 更新 DeepSeek-R1 MI355X SGLang 镜像#2691Oseltamivir wants to merge 2 commits into
Conversation
将 DeepSeek-R1 MI355X SGLang 分离式 MTP 配置升级到包含 AITER 准确性修复的新镜像，并追加性能变更日志。
|
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 For PR verification, add the 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 如需进行 PR 验证，请为此 PR 添加 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 |
将性能变更日志链接更新为替代 PR #2691。
Oseltamivir
added
full-sweep-fail-fast
all-evals
|
Claude finished @Oseltamivir's task in 1m 52s —— View job PR Review
LGTM - no blocking issues found Review notes:
|
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
LGTM — straightforward image tag bump with no bugs found.
What was reviewed: confirmed the diff touches only the dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp image tag in configs/amd-master.yaml and the matching perf-changelog.yaml entry; no other search-space, topology, or launch-flag fields changed.
Extended reasoning...
Overview
The PR bumps the Docker image for the dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp recipe in configs/amd-master.yaml from lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529 to v0.5.17-rocm720-mi35x-20260820, and adds a corresponding entry to perf-changelog.yaml documenting the AITER fixes picked up (masked-reduce and persistent-MLA synchronization) that address a known accuracy-corruption issue tracked upstream. This is a config-only change touching 2 files with a net diff of one modified line and one new changelog block; no launch scripts, topology, or search-space parameters are touched.
Security risks
None. This is a data-only YAML config change (image tag string + changelog metadata). No code execution paths, credentials, or user input handling are affected.
Level of scrutiny
Low. This is the standard, frequently-repeated 'refresh inference-engine image' pattern used throughout this repo (e.g. the adjacent Qwen3.5 and MiniMax refreshes visible in the same file). The change is mechanical, self-contained, and validated by the PR's own described process (YAML parsing, sweep-config generation, image digest/AITER-commit verification). The label is applied, so CI will exercise the new image against the existing search space before merge.
Other factors
The bug-hunting pass found no issues, and my own reading of the diff confirms only the image tag and changelog changed — the topology (prefill/decode worker counts, tp/ep, dp-attn, concurrency lists) is untouched, matching the PR description's claim of preserving the existing search space.
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=32335774883 |
1 participant
Summary
dsr1-fp4-mi355x-sglang-disagg-8k1k-mtpfromlmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529tolmsysorg/sglang-rocm:v0.5.17-rocm720-mi35x-20260820.d9e5ef7, which contains the stage-2 masked-reduce fix from flydsl moe: EP reduce path with masked gather + tuned-key fix ROCm/aiter#3377 and the persistent-MLA synchronization fix fromcdd6628.Validation
git diff --checkconfigs/amd-master.yaml,configs/runners.yaml, andperf-changelog.yamlwith PyYAML.generate_sweep_configs.py test-config; all emitted points use the new image and preserve the existing topology/search space.中文说明
dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp的镜像从lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529升级到lmsysorg/sglang-rocm:v0.5.17-rocm720-mi35x-20260820。d9e5ef7，其中包含 flydsl moe: EP reduce path with masked gather + tuned-key fix ROCm/aiter#3377 的第二阶段 masked-reduce 修复，以及cdd6628的 persistent-MLA 同步修复。main替代已关闭的 [AMD] Update DSR1 MI355X SGLang image / [AMD] 更新 DSR1 MI355X SGLang 镜像 #2435。验证
git diff --checkconfigs/amd-master.yaml、configs/runners.yaml和perf-changelog.yaml。generate_sweep_configs.py test-config生成目标配置；所有生成点均使用新镜像，并保留原有拓扑和搜索空间。