Skip to content

[Klaud Cold] Add MiMo-V2.6-Flash B200 vLLM DFlash AgentX recipe / [Klaud Cold] 新增 MiMo-V2.6-Flash B200 vLLM DFlash AgentX 配方 - #4742

Open
kimbochen wants to merge 9 commits into
mainfrom
feat/mimov2.6flash-b200-vllm-agentic-dflash
Open

kimbochen wants to merge 9 commits into
mainfrom
feat/mimov2.6flash-b200-vllm-agentic-dflash

Conversation

@kimbochen

@kimbochen kimbochen commented Nov 2, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

Adds DFlash speculative decoding for XiaomiMiMo/MiMo-V2.6-Flash-RL AgentX on B200 with upstream vLLM, as a new key, mimov2.6flash-fp4-b200-vllm-agentic-dflash.

Stacked on #4331. This branch is built on #4331, which commits the golden curve infx/golden_al_distribution/mimov2.6flash_dflash.yaml this key needs, and it targets main so the sweep runs. Until #4331 merges, this diff also shows #4331's collector and curve. The recipe itself does not depend on #4330, the non-speculative SGLang and vLLM keys.

What runs: 13 points, all with GPU-resident KV.

TP Draft tokens Synthetic AL Concurrency
8 7 4.08 1, 4
4 7 4.08 1, 4, 8, 16
4 3 2.97 32, 64
2 7 4.08 1, 4, 8
2 3 2.97 16, 32

Seven draft tokens give the longest acceptance where decode is latency-bound. At higher concurrency, verifying 8 tokens per step costs more compute than it saves, so those points verify 4 (3 drafts plus the current token).

Server: vllm/vllm-openai:v0.31.0 (pinned by digest), as in the non-speculative vLLM key of #4330, following vLLM's MiMo-V2.6-Flash-RL recipe:

  • speculative-config with method: dflash, the checkpoint's own BF16 dflash/ drafter, and greedy drafting, which is how the golden curve was collected.
  • cudagraph_mode: FULL_DECODE_ONLY, as in the recipe's DFlash example. Decode graphs cover concurrency × (1 + draft tokens), and admission stays at 2× concurrency for subagent fan-out.
  • All other flags match the non-speculative vLLM key: gpu-memory-utilization 0.95, max-model-len auto, max-num-batched-tokens 16384, mimo reasoning and tool-call parsers, thinking on.
  • VLLM_HTTP_TIMEOUT_KEEP_ALIVE=600, so the server keeps idle connections open longer than AIPerf leaves its pooled connections idle. In the first sweep, 41377885108, TP4 c64 lost two warmup requests to connection resets under vLLM's default 5 s keep-alive while the server stayed healthy.

Synthetic acceptance: the infx/srt_slurm connector reads the draft length from each point's speculative-config and sets rejection_sample_method: synthetic with the golden AL for thinking_on. vLLM v0.31.0 supports synthetic rejection sampling for dflash.

Draft path: vLLM loads a draft model only from a concrete local path, and <repo>/dflash is not a Hub model, so the recipe names the drafter inside the shared hub cache:

Local validation:

  • validate_perf_changelog passes.
  • infx.matrix.changed lists only this key's 13 points.
  • Each point binds to exactly one recipe variant through select_recipe, and build_overrides applies AL 4.08 at 7 draft tokens and 2.97 at 3.
  • The full infx/tests suite fails the same 31 tests on this branch and on main here, from missing local packages such as srtctl; CI runs them.

Sweep: run 41384884664 passed all 13 points and the gsm8k eval (strict match 0.972 at TP4 c64). It needed two re-runs of the canary for infrastructure failures: Slurm job 24818 was cancelled from outside the workflow, and AIPerf then hit Hugging Face's API rate limit (429) while loading the trace dataset. No profiled request failed at any point; the dropped records are all warmup requests.

Against the non-speculative vLLM key from #4330 (run 39323832019), same image and flags:

TP Concurrency Total tok/s/GPU, no spec → DFlash Median interactivity (tok/s/user), no spec → DFlash Interactivity gain
8 1 1,555 → 3,789 271 → 880 3.25×
8 4 3,116 → 5,116 273 → 910 3.34×
4 1 2,955 → 7,226 258 → 784 3.04×
4 4 6,133 → 10,338 259 → 811 3.14×
4 8 12,099 → 16,892 210 → 760 3.62×
4 16 19,546 → 29,210 104 → 673 6.49×
4 32 27,912 → 56,049 45 → 269 6.02×
4 64 30,024 → 54,908 16.5 → 47.0 2.85×
2 1 5,424 → 13,072 213 → 642 3.01×
2 4 11,736 → 18,304 205 → 657 3.21×
2 8 20,525 → 31,611 140 → 570 4.06×
2 16 23,006 → 51,707 37.1 → 260 7.01×
2 32 19,033 → 20,481 13.7 → 16.1 1.18×

Up to concurrency 8, interactivity rises about 3×, in line with the synthetic AL of 4.08. TP2 c32 is limited by KV capacity. Without speculation it already runs at 93% GPU KV usage with a 56% prefix hit rate; with the drafter also on the GPUs, usage reaches 99.8% and the hit rate falls to 33%, so DFlash gains little there.

Merge order: #4331 first. When #4330 is also merged, its MODELS.md row needs its "no speculative decoding" note replaced with this DFlash key, either here or in #4330, whichever lands second.

AI model disclosure
  • Model/version: Claude Opus 5.5 (claude-opus-5-5), via Claude Code. No delegated agents for this PR.
  • Role: vLLM source and recipe review, recipe and config authoring, local validation, sweep monitoring and fixes, and PR preparation.
PR checklist and change type

Type of Change

  • Bug fix
  • New feature
  • Configuration change
  • Documentation update
  • Other (please describe)

Checklist

  • I have completed the AI model disclosure and kept it current
  • I have tested my changes locally
  • I have updated documentation if necessary
  • If python -m infx.matrix.changed --base origin/main lists affected config keys, I have appended one new entry covering them to the physical end of inferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entries
  • If this PR appends an inferencex-e2e/perf-changelog.yaml entry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs): full-sweep-fail-fast (recommended), full-sweep-enabled, or non-canary-full-sweep-enabled. Optional modifiers all-evals, evals-only, and agentx-fast require a primary label; the last two block reuse while applied.
  • Before merging via reuse, an authorized maintainer (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

为 XiaomiMiMo/MiMo-V2.6-Flash-RL 在 B200 上基于上游 vLLM 的 AgentX 新增 DFlash 投机解码,对应新配置键 mimov2.6flash-fp4-b200-vllm-agentic-dflash。

叠加在 #4331 之上。 本分支基于 #4331(提交了该配置键所需的黄金曲线 infx/golden_al_distribution/mimov2.6flash_dflash.yaml),目标分支为 main,以便触发 sweep。#4331 合并前,本 PR 的 diff 也会显示 #4331 的采集脚本与曲线。配方本身不依赖 #4330(不带投机解码的 SGLang 与 vLLM 配置键)。

运行内容: 13 个点,KV 缓存均保留在 GPU 上。

TP 草稿 token 数 合成 AL 并发
8 7 4.08 1、4
4 7 4.08 1、4、8、16
4 3 2.97 32、64
2 7 4.08 1、4、8
2 3 2.97 16、32

解码受延迟限制时,7 个草稿 token 的接受长度最长;并发较高时,每步验证 8 个 token 的计算开销超过收益,因此这些点每步验证 4 个(3 个草稿加当前 token)。

服务配置: vllm/vllm-openai:v0.31.0(按 digest 固定),与 #4330 中不带投机解码的 vLLM 配置键相同,遵循 vLLM 的 MiMo-V2.6-Flash-RL 配方:

  • speculative-config 使用 method: dflash、检查点自带的 BF16 dflash/ 草稿模型与贪心草稿采样,与黄金曲线的采集方式一致。
  • cudagraph_mode: FULL_DECODE_ONLY,与配方中的 DFlash 示例一致。解码 CUDA graph 覆盖“并发 ×(1 + 草稿 token 数)”,准入仍为并发的 2 倍以支持子 agent 扇出。
  • 其余参数与不带投机解码的 vLLM 配置键相同:gpu-memory-utilization 0.95、max-model-len auto、max-num-batched-tokens 16384、mimo 推理与工具调用解析器,开启思考。
  • VLLM_HTTP_TIMEOUT_KEEP_ALIVE=600,使服务端保持空闲连接的时间长于 AIPerf 连接池中连接的空闲时间。首次 sweep 41377885108 中,在 vLLM 默认 5 秒 keep-alive 下,TP4 c64 有两个预热请求因连接被重置而失败,而服务端始终正常。

合成接受: infx/srt_slurm 连接器从每个点的 speculative-config 读取草稿长度,并按 thinking_on 的黄金 AL 设置 rejection_sample_method: synthetic。vLLM v0.31.0 支持对 dflash 使用合成拒绝采样。

草稿路径: vLLM 只能从具体的本地路径加载草稿模型,而 <repo>/dflash 不是 Hub 模型,因此配方直接指向共享 hub 缓存中的草稿目录:

本地验证:

  • validate_perf_changelog 通过。
  • infx.matrix.changed 只列出该配置键的 13 个点。
  • 每个点通过 select_recipe 恰好绑定一个配方变体,build_overrides 在 7 个草稿 token 时应用 AL 4.08,3 个时应用 2.97。
  • 完整的 infx/tests 在本分支与 main 上本地都失败同样的 31 项,原因是缺少 srtctl 等本地依赖;CI 会运行这些测试。

Sweep: 运行 41384884664 的 13 个点与 gsm8k 评估全部通过(TP4 c64 严格匹配 0.972)。canary 因基础设施问题重跑了两次:Slurm 作业 24818 在工作流之外被取消;随后 AIPerf 加载 trace 数据集时触发 Hugging Face API 限流(429)。所有点均无正式统计的请求失败,被丢弃的记录均为预热请求。

与 #4330 中不带投机解码的 vLLM 配置键(运行 39323832019,镜像与参数相同)对比:

TP 并发 每 GPU 总吞吐(tok/s),无投机 → DFlash 交互性中位数(tok/s/用户),无投机 → DFlash 交互性提升
8 1 1,555 → 3,789 271 → 880 3.25×
8 4 3,116 → 5,116 273 → 910 3.34×
4 1 2,955 → 7,226 258 → 784 3.04×
4 4 6,133 → 10,338 259 → 811 3.14×
4 8 12,099 → 16,892 210 → 760 3.62×
4 16 19,546 → 29,210 104 → 673 6.49×
4 32 27,912 → 56,049 45 → 269 6.02×
4 64 30,024 → 54,908 16.5 → 47.0 2.85×
2 1 5,424 → 13,072 213 → 642 3.01×
2 4 11,736 → 18,304 205 → 657 3.21×
2 8 20,525 → 31,611 140 → 570 4.06×
2 16 23,006 → 51,707 37.1 → 260 7.01×
2 32 19,033 → 20,481 13.7 → 16.1 1.18×

并发不超过 8 时,交互性提升约 3 倍,与合成 AL 4.08 相符。TP2 c32 受 KV 容量限制:不带投机解码时 GPU KV 使用率已达 93%,前缀命中率为 56%;加入草稿模型后,使用率达 99.8%,命中率降至 33%,因此 DFlash 在该点提升有限。

合并顺序: 先合并 #4331。#4330 也合并后,其 MODELS.md 行中“不使用投机解码”的说明需替换为本 DFlash 配置键,由两者中后合并的一方修改。

AI 模型使用说明: Claude Opus 5.5(claude-opus-5-5),通过 Claude Code 使用,本 PR 未委派其他 agent;负责 vLLM 源码与配方审阅、配方与配置编写、本地验证、sweep 监控与修复以及 PR 准备。

改动类型: 新功能、配置变更。

🤖 Generated with Claude Code

https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm

Managed user kimbo and others added 7 commits October 19, 2026 18:34
…speedbench):新增 MiMo-V2.6-Flash SGLang MTP AL 采集脚本

Measures SPEED-Bench coding acceptance length for MiMo-V2.6-Flash's
bundled MTP layers (SGLang multi-layer EAGLE, topk 1, depths 1-3) on
B300, thinking on, for the golden AL curve mimov2.6flash_mtp.yaml.

在 B300 上测量 MiMo-V2.6-Flash 自带 MTP 层(SGLang 多层 EAGLE,
topk 1,深度 1-3)在 SPEED-Bench coding 类别上的接受长度(开启思考),
用于生成 golden AL 曲线 mimov2.6flash_mtp.yaml。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…/ feat(speedbench):MiMo-V2.6-Flash AL 采集改用 vLLM DFlash

Replaces the SGLang MTP collector with a vLLM v0.31.0 collector for the
checkpoint's BF16 dflash/ drafter: draft lengths 1-7, thinking off and
on via enable_thinking, for the golden curve mimov2.6flash_dflash.yaml.

用 vLLM v0.31.0 采集脚本替换 SGLang MTP 采集脚本,测量检查点自带的
BF16 dflash/ 草稿模型:草稿长度 1-7,通过 enable_thinking 分别关闭和
开启思考,用于 golden 曲线 mimov2.6flash_dflash.yaml。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…eat/mimov2.6flash-speedbench-collector

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
…peedbench):加固 MiMo-V2.6-Flash vLLM AL 采集脚本

Run the benchmark client through vLLM's Python entrypoint so the Rust
client delegation cannot reject --speed-bench-output-len, --save-detailed
or --chat-template-kwargs, preflight those flags before any server start,
log a failing client exit per cell, and fail the job when no cell yields
an AL value. Mirrors the MiniMax-M3.1-Flash collector.

中文:基准客户端改走 vLLM 的 Python 入口,避免 Rust 客户端拒绝
--speed-bench-output-len、--save-detailed 与 --chat-template-kwargs;
在启动任何服务前预检这些参数,逐单元记录客户端异常退出,并在没有任何
单元得到 AL 值时让作业失败。做法与 MiniMax-M3.1-Flash 采集脚本一致。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
… is taken / fix(speedbench):8888 被占用时 MiMo AL 采集改用空闲端口

Run 41345416194 lost every cell to "Address already in use" on
dsxe-sa-b300-prd0-gpu-00: a process outside the Slurm job held port 8888 in
the shared network namespace. Report the holder and fall back to a free
port before the first server start.

中文:运行 41345416194 在 dsxe-sa-b300-prd0-gpu-00 上所有单元都因
"Address already in use" 失败:Slurm 作业之外的进程在共享网络命名空间中
占用了 8888 端口。现在在首次启动服务前报告占用者,并改用空闲端口。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
…t(golden-al):新增 MiMo-V2.6-Flash DFlash 黄金 AL 曲线

Commit infx/golden_al_distribution/mimov2.6flash_dflash.yaml from SPEED-Bench
coding run 41346734342 (B300, vLLM v0.31.0, BF16 dflash/ drafter, TP4,
temperature 1.0, top_p 0.95, output_len 4096). Every one of the 14 cells
completed 80/80 requests with no failures; thinking-on outputs all carry
reasoning tags and thinking-off outputs none. Register the curve in both
READMEs and the curve-name test.

中文:根据 SPEED-Bench coding 运行 41346734342(B300、vLLM v0.31.0、
BF16 dflash/ 草稿模型、TP4、temperature 1.0、top_p 0.95、output_len 4096)
提交 infx/golden_al_distribution/mimov2.6flash_dflash.yaml。14 个单元均
完成 80/80 请求且无失败;thinking-on 输出全部带推理标签,thinking-off
输出均不带。同时在中英文 README 与曲线名测试中登记该曲线。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
…aud Cold] 新增 MiMo-V2.6-Flash B200 vLLM DFlash AgentX 配方

Add mimov2.6flash-fp4-b200-vllm-agentic-dflash: upstream vLLM v0.31.0 with
the checkpoint's BF16 dflash/ drafter, greedy drafting and FULL_DECODE_ONLY
CUDA graphs, following vLLM's MiMo-V2.6-Flash-RL recipe. Synthetic
acceptance follows the golden curve mimov2.6flash_dflash.yaml: seven draft
tokens at low concurrency, three above TP4 c16 and TP2 c8. The target is
pinned to revision f657ba2f, and a setup script stages that snapshot so the
draft's local path exists before vLLM starts.

中文:新增 mimov2.6flash-fp4-b200-vllm-agentic-dflash:基于上游 vLLM
v0.31.0,使用检查点自带的 BF16 dflash/ 草稿模型、贪心草稿采样与
FULL_DECODE_ONLY CUDA graph,遵循 vLLM 的 MiMo-V2.6-Flash-RL 配方。合成
接受长度取自黄金曲线 mimov2.6flash_dflash.yaml:低并发用 7 个草稿 token,
TP4 c16、TP2 c8 以上用 3 个。目标模型固定在 f657ba2f 版本,并由 setup
脚本预先暂存该快照,确保 vLLM 启动前草稿模型的本地路径已存在。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
@github-actions

github-actions Bot commented Nov 2, 2026

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 run only when the PR appends an inferencex-e2e/perf-changelog.yaml entry and carries exactly one primary label: full-sweep-fail-fast (strongly recommended; canary plus per-matrix fail-fast), full-sweep-enabled (canary; matrix jobs continue after a failure), or non-canary-full-sweep-enabled (no canary or fail-fast). The modifiers all-evals, evals-only, and agentx-fast require a primary label. On fork PRs, a maintainer applies the label. See sweep labels and reuse.
  • 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:**只有当 PR 在 inferencex-e2e/perf-changelog.yaml 末尾追加了条目,并且恰好带有一个主标签时,才会运行扫描:full-sweep-fail-fast(强烈推荐;canary 加逐矩阵 fail-fast)、full-sweep-enabled(有 canary;矩阵任务在失败后继续运行)或 non-canary-full-sweep-enabled(无 canary,也无 fail-fast)。修饰标签 all-evals、evals-only 和 agentx-fast 必须与主标签一起使用。fork PR 的标签由维护者添加。参见扫描标签与复用。
  • **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。

@github-actions

github-actions Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

inferencex-e2e/infx diff: +30 -0

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。

…Flash 变更日志条目链接到 #4742

中文:在 perf-changelog 条目中填入 PR 链接 #4742。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
@kimbochen kimbochen added the full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended) label Nov 2, 2026

@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 on lines +12 to +14
DRAFT=/mnt/hf_hub_cache/models--XiaomiMiMo--MiMo-V2.6-Flash-RL/snapshots/$REVISION/dflash
for attempt in 1 2 3 4 5; do
if HF_HUB_CACHE=/mnt/hf_hub_cache hf download "$REPO" --revision "$REVISION" >/dev/null; then

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.

🟡 (optional) The new setup hook ignores the job's HF hub cache setting and always downloads into /mnt/hf_hub_cache. If the container's HF_HUB_CACHE points elsewhere, vLLM downloads the full target a second time, with no error. Line 14 sets HF_HUB_CACHE=/mnt/hf_hub_cache unconditionally, and line 12 checks the draft at the same constant path. AGENTS.md forbids replacing a caller-supplied setting this way. Fix: validate the caller's HF_HUB_CACHE with check_env_vars and fail clearly unless it is the /mnt/hf_hub_cache path that the recipe's speculative-config names. Then download with the caller's value unchanged.

Why this was flagged

The caller sets the cache: benchmark-tmpl.yml:103 sets HF_HUB_CACHE: '/mnt/hf_hub_cache/', and infx/launch/drivers/srt/init.py:89 mounts the host cache at request.hf_hub_cache. The hook at mimov2.6flash-dflash-draft.sh:14 ignores that value and passes a constant to hf download. Line 12 builds DRAFT from the same constant. vLLM in the same container loads the target XiaomiMiMo/MiMo-V2.6-Flash-RL at revision f657ba2f… from whatever HF_HUB_CACHE the container actually has. If that differs (another dispatcher or cluster mounts the cache elsewhere, or the variable is not forwarded), the hook writes the whole checkpoint to an unmounted or different directory. vLLM then downloads it again, and nothing reports the mismatch. On the base branch this hook does not exist. The sibling kimik3-atom-dspark-draft.sh:8 relies on the forwarded HF_HUB_CACHE instead. AGENTS.md Bash (mandatory) says to "never replace a supported override with an unconditional assignment" and that receiving scripts validate configuration instead of choosing it.

Verification: nit. Trigger: the job's HF_HUB_CACHE is something other than /mnt/hf_hub_cache. In mimov2.6flash-dflash-draft.sh, line 14 runs HF_HUB_CACHE=/mnt/hf_hub_cache hf download "$REPO" --revision "$REVISION", replacing the caller's HF_HUB_CACHE with a constant. If the two paths ever differ, the failure is silent. Severity stays nit because the deployed workflows set exactly this path.

# concrete local path, so the recipe points the draft at this snapshot's dflash/ in the
# shared hub cache. Shared-cache downloads can hit transient stale handles, hence the
# retries.
set -euo pipefail

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.

🟡 (optional) The new host-setup hook turns on nounset, which the repo's mandatory Bash rules forbid in active scripts. set -euo pipefail at line 7 is listed by name in AGENTS.md under "No nounset". Fix: use set -eo pipefail. The script references no possibly-unset variables, so nothing else changes.

Why this was flagged

AGENTS.md "Bash (mandatory)" says "No nounset: no set -u, set -o nounset, set -euo pipefail, or bash -u. Keep other options such as set -eo pipefail." The new file mimov2.6flash-dflash-draft.sh:7 is an active setup script that the new recipe agentic.yaml:18 references through setup_script. Line 7 is exactly set -euo pipefail. kimik3-atom-dspark-draft.sh:5 does the same, which is where the line was copied from. That is precedent for the violation, not an exception to the rule. The PR adds a new violation of a mandatory repo rule. Dropping -u fixes it with no behaviour change.

Verification: Triggering condition: always, because the file is a new active setup script. In mimov2.6flash-dflash-draft.sh, line 7 is set -euo pipefail. Under "Bash (mandatory)", AGENTS.md:48 says: "No nounset: no set -u, set -o nounset, set -euo pipefail, or bash -u." This script is active: the new recipe agentic.yaml:18 refers to it with setup_script: mimov2.6flash-dflash-draft.sh.

Comment on lines +7428 to +7430
# MiMo-V2.6-Flash AgentX on B200 with vLLM and the checkpoint's own DFlash drafter
# (dflash/, BF16), following vLLM's MiMo-V2.6-Flash-RL recipe. Synthetic acceptance
# follows infx/golden_al_distribution/mimov2.6flash_dflash.yaml.

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.

🟡 nit (optional): Header comments that describe a config, recipe or file break the repo's mandatory comment rule. sweep:^# (MiMo-V2.6-Flash|Stage the pinned|One variant per point) Fix: delete the 3-line header above the new master key at nvidia-master.yaml:7428-7430 and the file header at mimov2.6flash-dflash-draft.sh:2-6. Keep only short per-line technical comments, such as the existing "keep the two in sync" note.

Why this was flagged

AGENTS.md "Comments (mandatory, every file)" says "No header comments describing a file, topology, config, recipe, override, or section" and allows only short technical notes about a specific line. nvidia-master.yaml:7428-7430 adds a 3-line header describing the new mimov2.6flash-fp4-b200-vllm-agentic-dflash entry. It also cites provenance ("following vLLM's MiMo-V2.6-Flash-RL recipe"). mimov2.6flash-dflash-draft.sh:2-6 is a 5-line file header. agentic.yaml:51-57 is a 7-line section header above the overrides that restates the golden AL values and the variant layout. The rule is labelled mandatory, so these break repo convention. They add no runtime defect.

Verification: nit. The trigger is that the PR merges as written. Nothing breaks at runtime. AGENTS.md:54-58 says "No header comments describing a file, topology, config, recipe, override, or section". nvidia-master.yaml (new lines 7428-7430) puts a 3-line header above mimov2.6flash-fp4-b200-vllm-agentic-dflash. mimov2.6flash-dflash-draft.sh lines 2-6 are a 5-line file header.

("dsv4dsparkprob", {"method": "dspark"}, "dsv4-pro-0813-dspark"),
("dsv41flash", {"method": "dspark"}, "dsv41flash_dspark"),
("musespark", {"method": "dflash"}, "musespark_dflash"),
("mimov2.6flash", {"method": "dflash"}, "mimov2.6flash_dflash"),

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.

🟡 nit (optional): The new test row adds no coverage and fails if someone renames the checked-in curve. It runs the same default f"{model}_{method}" branch as the musespark row. It also asserts that mimov2.6flash_dflash.yaml exists, and AGENTS.md says tests like that should be deleted. Fix: drop the row; test_every_committed_curve_is_valid already validates the new curve.

Why this was flagged

In curve_name (infx/golden_al_distribution/curves.py:50-67), the prefix "mimov2.6flash" with method "dflash" takes no special branch. It returns f"{model}_{method}", the same path the existing musespark, dsv41flash and minimaxm31flash rows already cover. test_curve_name_resolves_committed_curves:54 then asserts (GOLDEN_DIR / f"{expected}.yaml").is_file(), which only pins the checked-in file. The row fails if someone renames or retires the curve, even when no code changes. AGENTS.md Tests says tests that "pin checked-in config" or "duplicate a covered branch must be deleted" (questions 3 and 4). test_every_committed_curve_is_valid:18-28 already loads and range-checks every committed curve, including this one.

Verification: Trigger: the new parametrized row in test_golden_al_distribution.py:42 always runs. In curves.py curve_name, "dflash" is not "eagle" or "nextn", so the method stays "dflash". That is the same default path the existing ("musespark", {"method": "dflash"}) row at line 41 already covers. The row would fail if that curve were renamed or removed with no code change.

kimbochen pushed a commit that referenced this pull request Nov 2, 2026
…at/mimov2.6flash-b200-sglang-agentic

Resolve perf-changelog.yaml with prepare_perf_changelog_merge (main's
bytes kept, the #4330 entry re-appended) and place the MiMo-V2.6-Flash
MODELS.md row by date between MiniMax-M3.1-Flash and Muse Spark Open,
pointing its speculative-decoding note at #4742.

中文:使用 prepare_perf_changelog_merge 解决 perf-changelog.yaml 冲突(保留
main 原有内容并重新追加 #4330 条目);将 MiMo-V2.6-Flash 在 MODELS.md 中的
行按日期放在 MiniMax-M3.1-Flash 与 Muse Spark Open 之间,并将其投机解码说明
指向 #4742。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm
@github-actions

github-actions Bot commented Nov 2, 2026 •

Copy link
Copy Markdown
Contributor

…le gaps / [Klaud Cold] 让 MiMo DFlash vLLM 连接撑过 AIPerf 空闲间隔

Sweep 41377885108 lost TP4 c64 when two AgentX warmup requests hit
"Connection reset by peer" on a live server: uvicorn's default 5 s
keep-alive closed pooled connections just as AIPerf reused them. Set
VLLM_HTTP_TIMEOUT_KEEP_ALIVE to 600, as the MiniMax-M3.1-Flash and Kimi
vLLM AgentX recipes do.

中文:sweep 41377885108 中 TP4 c64 失败:两个 AgentX 预热请求在服务正常运行
时遇到 "Connection reset by peer",原因是 uvicorn 默认 5 秒的 keep-alive 恰在
AIPerf 复用连接池中的连接时将其关闭。现将 VLLM_HTTP_TIMEOUT_KEEP_ALIVE 设为
600,与 MiniMax-M3.1-Flash 和 Kimi 的 vLLM AgentX 配方一致。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BGggnGqhy9dML7NM9ow3Fm

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

full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended)

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

1 participant