knowledge: curate the 2026-09-09 intake batch after review

Human curation of the bot's batch, addressing the Codex review:

- `DIFF-2y` -> `DIFF-2ac` and `DIFF-4w` -> `DIFF-4ac`: both IDs already
  head unrelated rules on sibling diffusion pages (checkpoint-loading,
  worker-observability); exact-ID routing must stay unambiguous.
- MMH3-4e contradicted MMH3-4a on the same NPU text-MLP trigger
  (`F.linear` on the raw weight vs. the module call). Fold the
  quantization-dispatch requirement from PR #6876 into MMH3-4a and drop
  the duplicate section.
- Add each cited PR to its page's `sources:` frontmatter.
- Route the new rules: Direct table rows for `DIFF-2ae`, `MCPMO-2e`,
  `MMH3-4d` (plus the existing `MMH3-4a`/`4b`), `QOMNI-1g`, and the
  nearest `_index.md` rows for every touched page.

Validators: check_knowledge_tree 0 errors, check_wiki_lint 0 errors,
test_knowledge_source green.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018MAFmwP3u5qAMDgHfM6LFi

Author: tzhouam

knowledge/repos/vllm-omni/components/configuration/_index.md

@@ -49,5 +49,6 @@ sources: ["claude-workflow-starter-private@296ea45", vllm_omni/config/]
 | 审查或新增 process 环境变量、stage `env` 和安全诊断输出 | [environment-variable contract](environment-variable-contract.md) |
 | 计算多 stage 显存预算 | [deployment memory budget](deployment-memory-budget.md) |
 | 添加新模型和注册点 | [adding a model](adding-a-model.md) |
-| composable strategy 的 axis、并行拓扑与 load balancing owner | [并行拓扑合同](rules-parallel-topology.md) |
+| composable strategy 的 axis、并行拓扑、load balancing owner 与 resolve_omni_config 统一解析 | [并行拓扑合同](rules-parallel-topology.md) |
+
 | 冻结 topology、辅助 stage 注入与模型专用 deploy profile | [topology 与部署 profile](rules-topology-profiles.md) |

knowledge/repos/vllm-omni/components/configuration/rules-parallel-topology.md

@@ -4,7 +4,7 @@ created: 2026-09-04
 updated: 2026-09-09
 type: rule
 tags: [vllm-omni, components, config]
-sources: [vllm_omni/config/composable_parallel/, vllm_omni/config/config_factory.py, vllm_omni/config/stage_config.py, "PR #5531"]
+sources: [vllm_omni/config/composable_parallel/, vllm_omni/config/config_factory.py, vllm_omni/config/stage_config.py, "PR #5531", "PR #5140"]
 confidence: high
 ---
 

knowledge/repos/vllm-omni/components/diffusion/_index.md

@@ -37,16 +37,19 @@ sources: ["PR #5543", vllm_omni/platforms/cuda/platform.py, vllm_omni/diffusion/
 | CustomOp XPU platform dispatch、PyTorch-native fallback、CUDA contract 与非同义 override 边界 | [CustomOp dispatch rules](rules-custom-op-dispatch.md) |
 | runtime temporary 与 loader-scoped parameter dtype、shared RMSNorm accuracy | [tensor dtype rules](rules-tensor-dtype.md) |
 | Wan VAE height/width spatial reshard、empty tail、attention extent | [Wan spatial-shard rules](rules-wan-spatial-shard.md) |
-| multi-DiT、dotted `_dit_modules`、loader-to-offloader handoff 与跨 Cache-DiT/compile/LoRA/offload lifecycle | [component lifecycle rules](rules-component-lifecycle.md) |
-| PEFT 与 distilled LoRA、startup fusion、delta/key/alpha、Qwen/Wan transformer mapping | [LoRA rules](rules-lora.md) |
+| multi-DiT、dotted `_dit_modules`、loader-to-offloader handoff 与跨 Cache-DiT/compile/LoRA/offload lifecycle、batch sampling-key 的 provided 标志 | [component lifecycle rules](rules-component-lifecycle.md) |
+
+| PEFT 与 distilled LoRA、startup fusion、delta/key/alpha、Qwen/Wan transformer mapping、PEFT suspend/resume | [LoRA rules](rules-lora.md) |
+
 | Blackwell FA4、显式/auto CUDA backend、per-role mask/SP pad；local FlashAttention deterministic opt-in、role-aware masked cross-attention、NPU packed mask-free/laser fallback、TRTLLM packed-padding 与 config propagation | [attention rules](rules-attention.md) |
 | SP auto-padding、`mask_sp_padding`、dense/varlen 与 advanced UAA 边界 | [SP padding rules](rules-sp-padding.md) |
 | video/audio mux、DLO DP wave、RPC reply ownership/result release、result queue、async pump、SHM ownership、async-output wait 与 shutdown | [output/runtime rules](rules-output-lifecycle.md) |
 | distilled continuous sigma schedule、boundary/step 语义与 modality shift | [sigma schedule rules](sigma-schedules.md) |
 | HunyuanImage3 Distil CFG、MeanFlow special-token / scheduler-r 合同 | [HunyuanImage3 HY3-8d](../../models/hunyuan-image3/rules.md) |
 | diffusion step 与 request/continuous batching；DIFF-1af BAGEL image step wave、packed state、geometry/CFG admission 与 fallback cleanup | [step and batching](step-and-batching.md) |
 | request-wave admission coalescing、stable window、deadline 与 finite config | [admission wait rules](rules-admission-wait.md) |
-| paged KV/cache 预算、native/backend/platform 闭环、GQA/Ring/Ulysses layout、FlashInfer plan、能力 metadata | [paged cache 与系统运行时规则](rules-system-runtime.md) |
+| paged KV/cache 预算、native/backend/platform 闭环、GQA/Ring/Ulysses layout、FlashInfer plan、能力 metadata、cache_backend None 规范化 | [paged cache 与系统运行时规则](rules-system-runtime.md) |
+
 | Scheduler-managed diffusion KV 的请求控制面、Hunyuan layout 与未实现边界 | [paged KV control plane](paged-kv-control-plane.md) |
 | Cache-DiT、TeaCache 和 prefix cache | [cache acceleration](cache-acceleration.md) |
 | TP/PP/SP/CFG/VAE/HSDP 等并行策略 | [parallelism](parallelism.md) |

knowledge/repos/vllm-omni/components/diffusion/rules-component-lifecycle.md

@@ -4,7 +4,7 @@ created: 2026-09-02
 updated: 2026-09-09
 type: rule
 tags: [vllm-omni, components, diffusion]
-sources: ["PR #5720", "PR #5853", "PR #5882", "PR #5884", "PR #6486", "PR #6591", vllm_omni/diffusion/cache/base.py, vllm_omni/diffusion/cache/cachedit/backend.py, vllm_omni/diffusion/cache/cachedit/runtime.py, vllm_omni/diffusion/lora/manager.py, vllm_omni/diffusion/models/interface.py, vllm_omni/diffusion/offloader/module_collector.py, vllm_omni/diffusion/offloader/startup.py, vllm_omni/diffusion/registry.py, vllm_omni/diffusion/sched/interface.py, vllm_omni/diffusion/worker/diffusion_model_runner.py, tests/diffusion/cache/test_cache_backends.py, tests/diffusion/cache/test_cache_dit_request_runtime.py, tests/diffusion/models/sana_video/test_cache_offload.py, tests/diffusion/test_diffusion_model_runner.py, tests/diffusion/test_diffusion_scheduler.py, "PR #6070", "vllm_omni/diffusion/models/ltx2/ltx2_recipes.py", "PR #6072"]
+sources: ["PR #5720", "PR #5853", "PR #5882", "PR #5884", "PR #6486", "PR #6591", vllm_omni/diffusion/cache/base.py, vllm_omni/diffusion/cache/cachedit/backend.py, vllm_omni/diffusion/cache/cachedit/runtime.py, vllm_omni/diffusion/lora/manager.py, vllm_omni/diffusion/models/interface.py, vllm_omni/diffusion/offloader/module_collector.py, vllm_omni/diffusion/offloader/startup.py, vllm_omni/diffusion/registry.py, vllm_omni/diffusion/sched/interface.py, vllm_omni/diffusion/worker/diffusion_model_runner.py, tests/diffusion/cache/test_cache_backends.py, tests/diffusion/cache/test_cache_dit_request_runtime.py, tests/diffusion/models/sana_video/test_cache_offload.py, tests/diffusion/test_diffusion_model_runner.py, tests/diffusion/test_diffusion_scheduler.py, "PR #6070", "vllm_omni/diffusion/models/ltx2/ltx2_recipes.py", "PR #6072", "PR #7078"]
 confidence: high
 ---
 
@@ -120,7 +120,7 @@ residency 留在模型 owner。规则入口与其他共享机制仍见 [Diffusio
   HWR and checkpoint mmap；另注入 unregistration failure，断言 retryable retention、backend drop 和
   distributed teardown ordering。^[PR #6486] ^[PR #6591]
 
-## DIFF-2y — batch-first sampling gate 的 provided 标志必须进入 RequestBatchSamplingParamsKey
+## DIFF-2ad — batch-first sampling gate 的 provided 标志必须进入 RequestBatchSamplingParamsKey
 
 - 触发：修改 `RequestBatchSamplingParamsKey`、`_build_sampling_params_key`，或 pipeline 从 batch 首请求读取 `*_provided` 再决定 guidance/image-guidance 行为。
 - 强制：凡 pipeline 用 “omitted vs explicit” provided 标志做 batch-local gate 的字段，都必须进入 request-mode 与 step-mode 的 sampling-params key；数值相等但 provided 不同的请求不得合批。当前合同要求 `guidance_scale_2_provided` 与数值 `guidance_scale_2` 一并参与 key。

knowledge/repos/vllm-omni/components/diffusion/rules-lora.md

@@ -4,7 +4,7 @@ created: 2026-09-02
 updated: 2026-09-09
 type: rule
 tags: [vllm-omni, components, diffusion]
-sources: ["PR #2783", docs/user_guide/diffusion/lora.md, vllm_omni/config/omni_config.py, vllm_omni/config/stage_config.py, vllm_omni/diffusion/data.py, vllm_omni/diffusion/lora/loader.py, vllm_omni/diffusion/lora/manager.py, vllm_omni/diffusion/lora/layers/base_linear.py, vllm_omni/diffusion/models/qwen_image/pipeline_qwen_image.py, vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py, vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2_i2v.py, vllm_omni/diffusion/utils/tf_utils.py, vllm_omni/diffusion/worker/diffusion_worker.py, vllm_omni/engine/async_omni_engine.py, vllm_omni/entrypoints/cli/serve.py, tests/diffusion/lora/test_loader.py, tests/diffusion/lora/test_lora_manager.py, tests/entrypoints/test_async_omni_diffusion_config.py, "PR #5500", "vllm_omni/diffusion/models/ltx2/ltx2_adapter_parser.py", "vllm_omni/diffusion/models/ltx2/ltx2_phase_adapter.py", "PR #6070", "PR #6476", "PR #6550", vllm_omni/diffusion/models/minimax_h3/lora.py, "PR #6268", benchmarks/kernels/benchmark_diffusion_lora_expand.py, tests/diffusion/lora/test_base_linear.py]
+sources: ["PR #2783", docs/user_guide/diffusion/lora.md, vllm_omni/config/omni_config.py, vllm_omni/config/stage_config.py, vllm_omni/diffusion/data.py, vllm_omni/diffusion/lora/loader.py, vllm_omni/diffusion/lora/manager.py, vllm_omni/diffusion/lora/layers/base_linear.py, vllm_omni/diffusion/models/qwen_image/pipeline_qwen_image.py, vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py, vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2_i2v.py, vllm_omni/diffusion/utils/tf_utils.py, vllm_omni/diffusion/worker/diffusion_worker.py, vllm_omni/engine/async_omni_engine.py, vllm_omni/entrypoints/cli/serve.py, tests/diffusion/lora/test_loader.py, tests/diffusion/lora/test_lora_manager.py, tests/entrypoints/test_async_omni_diffusion_config.py, "PR #5500", "vllm_omni/diffusion/models/ltx2/ltx2_adapter_parser.py", "vllm_omni/diffusion/models/ltx2/ltx2_phase_adapter.py", "PR #6070", "PR #6476", "PR #6550", vllm_omni/diffusion/models/minimax_h3/lora.py, "PR #6268", benchmarks/kernels/benchmark_diffusion_lora_expand.py, tests/diffusion/lora/test_base_linear.py, "PR #7195"]
 confidence: high
 ---
 
@@ -22,10 +22,13 @@ confidence: high
 | Wan dual transformer、high/low-noise file order、partial load | `DIFF-2n` | `WanLoraLoaderMixin` → `get_transformer_from_pipeline(name)` → `transformer`/`transformer_2` |
 | LoRA linear active output slices、inference expand accumulation、autograd/dtype fallback | `DIFF-2ab` | `diffusion/lora/layers/base_linear.py::DiffusionBaseLinearLayerWithLoRA.apply` |
 | legacy dynamic adapter hook、packed/stacked binding、DLO sidecar residency、activation rollback | `DIFF-2x` | `DiffusionLoRAManager::{_load_adapter,_bind_adapter_weights,_activate_adapter}` → model pipeline hook |
+| PEFT deactivate/suspend、slice-mask resume、同 adapter+scale 再激活不 re-upload | `DIFF-2ae` | `DiffusionLoRAManager` deactivate/activate → `DiffusionBaseLinearLayerWithLoRA::{suspend_lora,resume_lora}` |
+
 
 | 审查组 | 什么时候触发 | 规则 ID |
 |---|---|---|
-| `checkpoint-distributed` | diffusion LoRA backend、checkpoint、融合与 transformer mapping | `DIFF-2l`, `DIFF-2m`, `DIFF-2n`, `DIFF-2x` |
+| `checkpoint-distributed` | diffusion LoRA backend、checkpoint、融合与 transformer mapping | `DIFF-2l`, `DIFF-2m`, `DIFF-2n`, `DIFF-2x`, `DIFF-2ae` |
+
 
 ## DIFF-2l — backend 是 startup 配置，不是 request 字段
 

knowledge/repos/vllm-omni/components/diffusion/rules-system-runtime.md

@@ -4,7 +4,7 @@ created: 2026-09-03
 updated: 2026-09-09
 type: rule
 tags: [vllm-omni, components, diffusion]
-sources: ["PR #5255", "PR #5344", "PR #5543", "PR #5838", "PR #6094", "PR #6102", "PR #6385", "PR #6340", "PR #6714", "PR #6814", "PR #6563", "PR #5716", "PR #6786", vllm_omni/diffusion/attention/, vllm_omni/diffusion/attention/parallel/ulysses.py, vllm_omni/diffusion/attention/parallel/ring_kernels.py, vllm_omni/diffusion/diffusion_kv/, vllm_omni/diffusion/distributed/cfg_parallel.py, vllm_omni/diffusion/distributed/parallel_state.py, vllm_omni/diffusion/worker/diffusion_model_runner.py, vllm_omni/platforms/interface.py, vllm_omni/platforms/npu/platform.py, tests/diffusion/diffusion_kv/, tests/diffusion/distributed/test_cfg_parallel.py, tests/diffusion/attention/test_piecewise_attn.py, tests/diffusion/attention/test_ulysses_uaa.py, "PR #5491", "PR #5194", "vllm_omni/diffusion/data.py", "vllm_omni/diffusion/utils/hf_utils.py"]
+sources: ["PR #5255", "PR #5344", "PR #5543", "PR #5838", "PR #6094", "PR #6102", "PR #6385", "PR #6340", "PR #6714", "PR #6814", "PR #6563", "PR #5716", "PR #6786", vllm_omni/diffusion/attention/, vllm_omni/diffusion/attention/parallel/ulysses.py, vllm_omni/diffusion/attention/parallel/ring_kernels.py, vllm_omni/diffusion/diffusion_kv/, vllm_omni/diffusion/distributed/cfg_parallel.py, vllm_omni/diffusion/distributed/parallel_state.py, vllm_omni/diffusion/worker/diffusion_model_runner.py, vllm_omni/platforms/interface.py, vllm_omni/platforms/npu/platform.py, tests/diffusion/diffusion_kv/, tests/diffusion/distributed/test_cfg_parallel.py, tests/diffusion/attention/test_piecewise_attn.py, tests/diffusion/attention/test_ulysses_uaa.py, "PR #5491", "PR #5194", "vllm_omni/diffusion/data.py", "vllm_omni/diffusion/utils/hf_utils.py", "PR #7041"]
 confidence: high
 ---
 
@@ -206,7 +206,7 @@ confidence: high
 - 禁止：Worker 自行分配或释放 Scheduler-owned logical blocks；把部分 row 安装、native append/apply 异常或 stale snapshot 当作成功；从 padding 猜异构 prefix 的逻辑布局；在清理或 wake refresh 后继续复用旧的 native metadata/buffer view。
 - 验收：CPU/mock 覆盖 rank-local config、请求/上下文 row mapping、重复/过期/冲突 generation、非法 block 与容量、append/apply rollback、幂等清理和 wake refresh；GPU/NPU 另验证非连续 BlockTables、32Q/8KV GQA、异构 prefix 与 piecewise attention。Hunyuan paged request execution 不证明 `denoise_step`、cross-request prefix reuse、AR KV、negative CFG、Ring 或 AllGather。^[PR #6102] ^[PR #6563]
 
-## DIFF-4w — 声明为 str 的 diffusion cache_backend 必须在 kwargs 边界把显式 None 规范成 none
+## DIFF-4ac — 声明为 str 的 diffusion cache_backend 必须在 kwargs 边界把显式 None 规范成 none
 
 - 触发：修改 `normalize_omni_diffusion_kwargs`、`OmniDiffusionConfig.cache_backend`，或 pipeline/runner 对 cache backend 的 admission 校验。
 - 强制：字段声明为 `str` 且 canonical “无 cache” sentinel 为 `"none"` 时，key 缺失才允许走 env/`"none"` 默认；调用方传入显式 `None`（如 CLI `default=None`）必须在 kwargs 边界规范成 `"none"`，且不得回落到 `DIFFUSION_CACHE_BACKEND` 查找。下游校验可把残留 `None` 当 `"none"` 作 defense-in-depth，但不能代替边界规范化。

knowledge/repos/vllm-omni/models/minicpm-o-4-5/rules.md

@@ -4,7 +4,7 @@ created: 2026-07-20
 updated: 2026-09-09
 type: rule
 tags: [vllm-omni, models, model-executor]
-sources: ["PR #3642", "PR #5165", "PR #5382", "PR #5524", "PR #5638", "PR #5792", "PR #5869", "PR #6056", "PR #6154", "PR #6170", "PR #6318", "PR #6828", tests/dfx/perf/tests/test_minicpmo_4_5.json, tests/dfx/perf/tests/test_minicpmo_4_5_duplex_seed_tts.json, tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py, tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py, tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py, tests/e2e/online_serving/test_minicpmo_4_5.py, tests/e2e/online_serving/test_minicpmo_4_5_duplex.py, tests/e2e/online_serving/test_minicpmo_4_5_expansion.py, tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py, vllm_omni/benchmarks/data_modules/seed_tts_dataset.py, vllm_omni/benchmarks/data_modules/seed_tts_eval.py, vllm_omni/benchmarks/patch/patch.py, vllm_omni/deploy/minicpmo_4_5.yaml, vllm_omni/experimental/fullduplex/client.py, vllm_omni/entrypoints/duplex/chat_fallback.py, vllm_omni/entrypoints/duplex/realtime_input.py, vllm_omni/entrypoints/duplex/session_runner.py, vllm_omni/entrypoints/duplex/serving.py, vllm_omni/entrypoints/duplex/vad.py, vllm_omni/model_executor/models/minicpmo_4_5/duplex/adapter.py, vllm_omni/model_executor/models/cosyvoice3/code2wav_core/hifigan.py, vllm_omni/model_executor/models/minicpmo_4_5/batched_token2wav.py, vllm_omni/model_executor/models/minicpmo_4_5/cuda_graph_wrapper.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_code2wav.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_omni_tts.py, vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py, tests/model_executor/models/minicpmo_4_5/test_audio_chunk_mask.py, tests/model_executor/models/minicpmo_4_5/test_cfm_graph_capture_gating.py, tests/model_executor/models/minicpmo_4_5/test_code2wav_batching.py, tests/model_executor/models/minicpmo_4_5/test_cuda_graph_wrapper.py, tests/model_executor/models/minicpmo_4_5/test_pipeline.py, tests/model_executor/models/minicpmo_4_5/test_talker_batching.py, tests/model_executor/models/minicpmo_4_5/test_vision_flash_attention.py, "PR #6082", "PR #5604", "PR #6274", "PR #6346", "PR #6397", "PR #6406", "PR #6458", "PR #6587", "PR #6619", "PR #6757", "PR #6529", "PR #6772", vllm_omni/entrypoints/duplex/protocol.py]
+sources: ["PR #3642", "PR #5165", "PR #5382", "PR #5524", "PR #5638", "PR #5792", "PR #5869", "PR #6056", "PR #6154", "PR #6170", "PR #6318", "PR #6828", tests/dfx/perf/tests/test_minicpmo_4_5.json, tests/dfx/perf/tests/test_minicpmo_4_5_duplex_seed_tts.json, tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py, tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py, tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py, tests/e2e/online_serving/test_minicpmo_4_5.py, tests/e2e/online_serving/test_minicpmo_4_5_duplex.py, tests/e2e/online_serving/test_minicpmo_4_5_expansion.py, tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py, vllm_omni/benchmarks/data_modules/seed_tts_dataset.py, vllm_omni/benchmarks/data_modules/seed_tts_eval.py, vllm_omni/benchmarks/patch/patch.py, vllm_omni/deploy/minicpmo_4_5.yaml, vllm_omni/experimental/fullduplex/client.py, vllm_omni/entrypoints/duplex/chat_fallback.py, vllm_omni/entrypoints/duplex/realtime_input.py, vllm_omni/entrypoints/duplex/session_runner.py, vllm_omni/entrypoints/duplex/serving.py, vllm_omni/entrypoints/duplex/vad.py, vllm_omni/model_executor/models/minicpmo_4_5/duplex/adapter.py, vllm_omni/model_executor/models/cosyvoice3/code2wav_core/hifigan.py, vllm_omni/model_executor/models/minicpmo_4_5/batched_token2wav.py, vllm_omni/model_executor/models/minicpmo_4_5/cuda_graph_wrapper.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_code2wav.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py, vllm_omni/model_executor/models/minicpmo_4_5/minicpmo_4_5_omni_tts.py, vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py, tests/model_executor/models/minicpmo_4_5/test_audio_chunk_mask.py, tests/model_executor/models/minicpmo_4_5/test_cfm_graph_capture_gating.py, tests/model_executor/models/minicpmo_4_5/test_code2wav_batching.py, tests/model_executor/models/minicpmo_4_5/test_cuda_graph_wrapper.py, tests/model_executor/models/minicpmo_4_5/test_pipeline.py, tests/model_executor/models/minicpmo_4_5/test_talker_batching.py, tests/model_executor/models/minicpmo_4_5/test_vision_flash_attention.py, "PR #6082", "PR #5604", "PR #6274", "PR #6346", "PR #6397", "PR #6406", "PR #6458", "PR #6587", "PR #6619", "PR #6757", "PR #6529", "PR #6772", vllm_omni/entrypoints/duplex/protocol.py, "PR #7071"]
 confidence: high
 ---
 
@@ -20,6 +20,8 @@ confidence: high
 |---|---|
 | version/registry、processor、remote code | `MCPMO-1a`、`MCPMO-2a` |
 | Whisper/APM 或 SigLIP attention | `MCPMO-2b`、`MCPMO-2c` |
+| audio_feature_lens ragged slices、encoder batch TensorShape | `MCPMO-2e` |
+
 | TTS/Code2Wav/TRT、CUDA Graph | `MCPMO-1b`–`MCPMO-1e`；[CUDA graphs](rules-cuda-graphs.md) |
 | batch、runtime info、reference-audio handoff | `MCPMO-3a`–`MCPMO-3e`；[Code2Wav batching](rules-code2wav-batching.md) |
 | native duplex、sampling budget、shipping profile、playback ACK | `MCPMO-4a`–`MCPMO-4h`；[duplex](rules-duplex.md) |

knowledge/repos/vllm-omni/models/minimax-h3/_index.md

@@ -159,6 +159,7 @@ text-encoder fused-source 完整性正文见 [loading rules](rules-loading.md)
 部署和硬件证据正文见 [deployment rules](rules-deployment.md)；conditioned VAE 确定性、modular task 选择与 request 级 Cache-DiT/TeaCache/sigma schedule/Turbo LoRA 生命周期见 [缓存与任务生命周期规则](rules-cache-task.md)。
 
 H3 VAE decoder 的 model-local eager dispatch、remote-code eligibility、exactness guards、selective
-FP16 materialization 与 compile/spatial-parallel fallback 见 [VAE eager-ops rules](rules-vae-ops.md)。
+FP16 materialization、keyframe encode 的 cuDNN/TF32 pin 与 compile/spatial-parallel fallback 见 [VAE eager-ops rules](rules-vae-ops.md)
+。
 Qwen3-VL text encoder 的 cuDNN SDPA process-global-state restore、encoder-rank/VAE boundary 和
 CPU-only validation limit 见 [encoder state rules](rules-encoder-state.md)。