Skip to content

knowledge: daily intake batch 14 - #159

Open
tzhouam wants to merge 1 commit into
mainfrom
knowledge/intake-2026-09-14
Open

tzhouam wants to merge 1 commit into
mainfrom
knowledge/intake-2026-09-14

Conversation

@tzhouam

@tzhouam tzhouam commented Sep 14, 2026

Copy link
Copy Markdown
Collaborator

Daily knowledge-intake batch from omni-reviewbot: executable rules distilled from merged PRs and copilot bugfix runs, append-only per the knowledge contract. Merging this PR is the human promotion gate — review the rules like any other knowledge edit.

Proposed rules

  • knowledge/repos/vllm-omni/ci/rules-amd.mdOMNI-CI-2i (sources: PR #7395)
  • knowledge/repos/vllm-omni/components/configuration/rules-legacy-engine-args.mdVOMNI-CFG-1u (sources: PR #7390)
  • knowledge/repos/vllm-omni/components/serving/rules-request-input.mdSERV-4r (sources: PR #4167)
  • knowledge/repos/vllm-omni/components/distributed/rules.mdDIST-1l (sources: PR #6889)
  • knowledge/repos/vllm-omni/models/cosmos3/rules.mdCOSMOS-1c (sources: PR #7427)
  • knowledge/repos/vllm-omni/components/diffusion/rules-lora.mdDIFF-2ag (sources: PR #5907)
  • knowledge/repos/vllm-omni/components/serving/rules-upstream-compat.mdSERV-7e (sources: PR #7426)
  • knowledge/repos/vllm-omni/components/model-executor/rules-loader-contract.mdEXEC-2j (sources: PR #7384)

Source events

  • merged_pr PR #7171: [Model][ERNIE-Image] Delay AdaLN modulation broadcast
  • merged_pr PR #7167: [Kernel][MiniMax-H3] Run Q/K RMSNorm-RoPE in one launch
  • merged_pr PR #7395: [CI][ROCm] Align AMD image with vLLM 0.29
  • merged_pr PR #7384: [Bugfix] Add embed_multimodal to MiniCPM-o 4.5 omni LLM class
  • merged_pr PR #6841: [Model] Add LingBot World Ulysses sequence parallelism
  • merged_pr PR #6853: [Feature][TTS] Add Speech API streaming metrics
  • merged_pr PR #7430: [Bugfix][Model] Fix FLUX.2 Klein multi-image edit metadata
  • merged_pr PR #7426: [BugFix] Fix leftovers of the legacy OpenAI realtime API event names
  • merged_pr PR #7385: [Model] Add Tencent AuK speech generation and editing (encoder + diffusion pipeline)
  • merged_pr PR #7441: [XPU][Docker] Align XPU image and CI with vLLM v0.29.0
  • merged_pr PR #7427: [Bugfix] Add explicit error when using CFGP with distilled Cosmos3 models
  • merged_pr PR #7094: [Perf][Diffusion] Run MammothModa2 DiT attention through the shared attention layer
  • merged_pr PR #7390: [Bugfix] Give model CLI flags typed owners in the Omni config
  • merged_pr PR #4167: [Bugfix] Require a model for vllm serve --omni (fixes #4158)
  • merged_pr PR #6889: [Bugfix] Send a downstream terminal chunk when a parked stage ends
  • merged_pr PR #7433: [NPU] upgrade to v0.29.0
  • merged_pr PR #5128: [Bugfix][Model][Lance] Support decoded video frames in video editing
  • merged_pr PR #4876: Optimize CosyVoice3 Stage1 flow batching
  • merged_pr PR #5907: [Refactor][Diffusion] Remove model-specific names from LoRA and ModelOpt loader defaults
  • merged_pr PR #7018: [3/N] Encode streamed video on the worker with bounded batching

Public SDK curation result

{
  "batch_id": "sha256:052423d86200f0f9cbb4a69c7168a4eab22fc77789a2d0c4e622bd195f041c42",
  "success": true,
  "attempted": 8,
  "applied": 8,
  "accepted_indexes": [
    0,
    1,
    2,
    3,
    4,
    5,
    6,
    7
  ],
  "rejected_indexes": [],
  "updated_document_ids": [
    "knowledge/repos/vllm-omni/ci/rules-amd.md",
    "knowledge/repos/vllm-omni/components/configuration/rules-legacy-engine-args.md",
    "knowledge/repos/vllm-omni/components/diffusion/rules-lora.md",
    "knowledge/repos/vllm-omni/components/distributed/rules.md",
    "knowledge/repos/vllm-omni/components/model-executor/rules-loader-contract.md",
    "knowledge/repos/vllm-omni/components/serving/rules-request-input.md",
    "knowledge/repos/vllm-omni/components/serving/rules-upstream-compat.md",
    "knowledge/repos/vllm-omni/models/cosmos3/rules.md"
  ],
  "updated_on": "2026-09-14",
  "validators": [
    {
      "validator_id": "knowledge/tools/check_knowledge_tree.py",
      "passed": true,
      "status": "passed",
      "returncode": 0,
      "output": "提醒:文件接近拆分线:general/review/guides/review-execution-contract.md (183 个非空行,21548 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/ci/rules.md (243 个非空行,27775 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/configuration/rules.md (174 个非空行,30403 bytes)\n提醒:目录有 15 个普通页面,应该考虑分类:repos/vllm-omni/components/configuration\n提醒:文件接近拆分线:repos/vllm-omni/components/diffusion/rules-attention.md (190 个非空行,25118 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/diffusion/rules-checkpoint-loading.md (211 个非空行,26702 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/diffusion/rules-output-lifecycle.md (147 个非空行,21047 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/diffusion/rules-system-runtime.md (189 个非空行,27138 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/diffusion/rules.md (172 个非空行,27612 bytes)\n提醒:目录有 22 个普通页面,应该考虑分类:repos/vllm-omni/components/diffusion\n提醒:文件接近拆分线:repos/vllm-omni/components/model-executor/rules-bridge-batch.md (134 个非空行,18619 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/model-executor/rules.md (193 个非空行,31439 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/scheduler/rules.md (299 个非空行,32496 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/serving/rules-engine-lifecycle.md (246 个非空行,32271 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/components/serving/rules.md (196 个非空行,31197 bytes)\n提醒:目录有 12 个普通页面,应该考虑分类:repos/vllm-omni/components/serving\n提醒:文件接近拆分线:repos/vllm-omni/models/cosmos3/rules.md (136 个非空行,16424 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/hunyuan-image3/rules.md (137 个非空行,25387 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/minicpm-o-4-5/rules.md (258 个非空行,30441 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/minimax-h3/rules-cache-task.md (204 个非空行,28481 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/minimax-h3/rules-deployment.md (236 个非空行,27707 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/minimax-h3/rules.md (183 个非空行,32421 bytes)\n提醒:文件接近拆分线:repos/vllm-omni/models/qwen3-tts/rules.md (190 个非空行,20981 bytes)\n知识目录检查通过:0 个错误,23 个提醒"
    },
    {
      "validator_id": "knowledge/tools/check_wiki_lint.py",
      "passed": true,
      "status": "passed",
      "returncode": 0,
      "output": "wiki lint 通过:0 个错误,0 个提醒(共 387 页)"
    }
  ],
  "rolled_back": false
}

The vllm-omni release audit runs in CI on this PR as usual.

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Sep 14, 2026

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review Completed 2026-09-14T07:35:28.496025Z fbeb2c2 PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: fbeb2c2860

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

- 禁止:让 residual `disable_log_stats` 落入 `resolve_omni_config` / `VllmOmniConfig` 并报 “no structured config owner”;为通过校验而放宽真正的 stage engine-arg ownership。
- 验收:断言字段在 `_NON_STAGE_ENGINE_CLI_FIELDS` 且不在 global stage CLI fields;engine 与 headless 解析后 kwargs/`cli_overrides` 不含该 alias;带 alias 的 TTS/structured pipeline 仍能构造。^[PR #7237]

## VOMNI-CFG-1u — 用户可见的 upstream ModelConfig CLI 必须有 typed stage owner

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Add the new rules to the Direct quick maps

When a PR about these ModelConfig flags is reviewed, Direct returns components/configuration/rules.md and exposes only its Direct section, whose strict-normalization row still ends at 1h plus 1s/1t; consequently VOMNI-CFG-1u is never presented to the reviewer. The same omission affects the newly added SERV-4r, SERV-7e, EXEC-2j, DIFF-2ag, DIST-1l, and COSMOS-1c in their corresponding owner/model maps, so update those Direct tables or ranges as part of this promotion.

AGENTS.md reference: knowledge/AGENTS.md:L16-L16

Useful? React with 👍 / 👎.

- 触发:修改 realtime WebSocket、video stream serving、示例客户端或协议文档中的音频 delta/done 事件名。
- 强制:服务端发出的增量与终态音频事件类型必须是 `response.output_audio.delta` / `response.output_audio.done`(及配套 transcript 命名),与已迁移的 OpenAI realtime 合同一致;示例与测试断言同一集合。
- 禁止:在任一生产发送路径残留 legacy `response.audio.delta` / `response.audio.done`;只改文档/示例而漏改 `realtime_connection` 或 `serving_video_stream`/`video_stream_base`。
- 验收:duplex/realtime/video-stream 测试收集到的音频事件类型集合等于 `response.output_audio.*`,且不接受仅 legacy 名作为成功合同。^[PR #7426]

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Record the new PRs in page-level sources

Each new section cites its PR only in the body while leaving the page's frontmatter sources: list unchanged—for example, this page omits PR #7426. doc/knowledge/SCHEMA.md requires PR-learning provenance in both page-level sources: and the paragraph citation, so all eight modified pages now advertise an incomplete evidence set to metadata-based consumers; add each proposed rule's PR to its target page's sources:.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants