Skip to content

feat(agentx): bump Kimi-K3 FP4 MI355X ATOM image to 0924 and track recipe - #3407

Open
gbyu-amd wants to merge 4 commits into
mainfrom
amd/kimik3-atom-agentx-0924
Open

gbyu-amd wants to merge 4 commits into
mainfrom
amd/kimik3-atom-agentx-0924

Conversation

@gbyu-amd

@gbyu-amd gbyu-amd commented Sep 24, 2026 •

Copy link
Copy Markdown
Collaborator

Track the checked-in ATOM recipe recipes/Agentic-Kimi-K3.md as retuned in ROCm/ATOM#2382, on image kimi_k3_agentic_0924.

The published concurrency set [1, 4, 14, 16, 48, 56, 72] is unchanged; no points are added or dropped.

  • ATOM_USE_FLYDSL_FP8_PREFILL_ATTN=1 on every band. ATOM defaults it to 0, so the recipe's prefill attention path was not reached before this change.
  • From concurrency 16 up, ATOM_PREFILL_DECODE_INTERVAL=4 and ATOM_PREFILL_DELAYER_MAX_QUEUE_MS=5000 hold a ready prefill for four decode passes instead of interleaving it into every step. This is a threshold, not a band: concurrency 1, 4 and 14 run without it.

max-num-seqs, max-num-batched-tokens, gpu-memory-utilization, the CUDA-graph ladder, dcp-size, draft depth, synthetic acceptance, ReplaySSM placement, AITER_REUSE_IDENTICAL_COMM_GROUPS and LMCache sizing are unchanged from #3207.

Re-created on an in-repo amd/ branch so sweep dispatch and labels (AMD, agentx, full-sweep-enabled) apply.

AI model disclosure

Prepared with Claude Code using claude-opus-5 (recipe reconciliation, edits, changelog entry). No other model contributed.

…cipe

Track recipes/Agentic-Kimi-K3.md as retuned in ROCm/ATOM#2382:
enable FlyDSL FP8 prefill attention on every band, and hold a ready
prefill for four decode passes from concurrency 16 up. The published
concurrency set and every other launch argument are unchanged.

将 MI355X Kimi-K3 FP4 ATOM AgentX 提交切换到 0924 镜像,并跟随
ROCm/ATOM#2382 重调后的 recipe:全部并发开启 FlyDSL FP8 prefill
attention;并发 16 及以上时让就绪的 prefill 等待 4 个 decode 轮次。
已发布的并发点集合与其余启动参数保持不变。

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@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 only run on labeled PRs. Add full-sweep-fail-fast (strongly recommended); use full-sweep-enabled only when matrix jobs should continue after a failure.
  • 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:**扫描仅在带有标签的 PR 上运行。强烈建议添加 full-sweep-fail-fast;仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。
  • **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。

将 perf-changelog 条目的 pr-link 指向 PR 3407。

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

@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.

Nothing blocking. The comments below are optional suggestions. There is no need to push a fix for them before merging.

Comment thread perf-changelog.yaml Outdated
@github-actions

github-actions Bot commented Sep 24, 2026 •

Copy link
Copy Markdown
Contributor

Comment thread configs/amd-master.yaml Outdated
…1613

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@functionstackx

Copy link
Copy Markdown
Collaborator

InferenceX has switched away from unmaintainable bash scripts to YAML files that don't repeat the same stuff over and over again. Please merge the latest main into this PR: we have migrated single-node AgentX onto native srt-slurm (#3428), so AgentX configs are now declarative YAML recipes, not per-config 1000+ line bash slop scripts. Please also delete the old benchmarks/single_node/** scripts (see this recipe for the new format).

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

agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

3 participants