Skip to content

AMD][MI35X] 0706 DSV4 sglang mtp#2108

Open
1am9trash wants to merge 3 commits into
mainfrom
dsv4-mi355-sgl-0706-mtp
Open

AMD][MI35X] 0706 DSV4 sglang mtp#2108
1am9trash wants to merge 3 commits into
mainfrom
dsv4-mi355-sgl-0706-mtp

Conversation

@1am9trash

Copy link
Copy Markdown
Collaborator

No description provided.

@github-actions

This comment was marked as duplicate.

4 similar comments
@github-actions

This comment was marked as duplicate.

@github-actions

This comment was marked as duplicate.

@github-actions

This comment was marked as duplicate.

@github-actions

github-actions Bot commented Jul 7, 2026

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

@Klaud-Cold

This comment was marked as duplicate.

Comment thread benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang_mtp.sh
@github-actions

This comment was marked as duplicate.

@github-actions

github-actions Bot commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

1 similar comment
@github-actions

github-actions Bot commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

1am9trash and others added 3 commits July 7, 2026 00:37
The script sourced ../benchmark_lib.sh, but the lib lives at
benchmarks/benchmark_lib.sh (two levels up from fixed_seq_len/), so every
lib function (check_env_vars, wait_for_server_ready, run_benchmark_serving,
...) was undefined and the run produced no result JSON (run 28836023139).
Matches the ../../benchmark_lib.sh path used by sibling scripts like
dsv4_fp4_mi355x_sglang.sh.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@functionstackx functionstackx force-pushed the dsv4-mi355-sgl-0706-mtp branch from 45ce009 to ff3f169 Compare July 7, 2026 04:39
@github-actions

github-actions Bot commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

@seungrokj

Copy link
Copy Markdown
Collaborator

@1am9trash
can you take a look at this ? I canceled the job due to this:
FAIL: gsm8k exact_match,strict-match = 0.8362 (< 0.91 from models.dsv4)
FAIL: gsm8k exact_match,flexible-extract = 0.8415 (< 0.91 from models.dsv4)

https://github.com/SemiAnalysisAI/InferenceX/actions/runs/28841974603/job/85556419336

@1am9trash

Copy link
Copy Markdown
Collaborator Author

This 2 PR may fix the mtp accuracy issue. Will bump the version after daily image build tomorrow.

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.

4 participants