panwudi · panwudi · Jun 10, 2026 · Jun 5, 2026 · Jun 6, 2026 · Jun 10, 2026
diff --git a/.gitignore b/.gitignore
@@ -125,3 +125,12 @@ uv.lock
 # venvstacks build artifact: regenerated from venvstacks.toml + pyproject.toml
 # by packaging/build.py:_generate_venvstacks_toml() on every Swift app build.
 packaging/_venvstacks_resolved.toml
+.claude/
+
+# Video generation artifacts (job outputs live under {base_path}, never in-repo;
+# these guard against measurement/test runs writing into the worktree)
+*.mp4
+*.mp4.metadata.json
+video-jobs/
+video-artifacts/
+p0_video/
diff --git a/docs/upstream-sync.md b/docs/upstream-sync.md
@@ -427,3 +427,29 @@ Qwen-Gemma / oQ)的相关度。
   破坏部分 HTTP 客户端 / Copilot CLI
 
 > 下次 review 上游 open PR 时,把结论(引入 / 跳过)回填到对应小节。
+
+---
+
+## 2026-06-11 分化标记: 视频生成引擎 (fmlx 自有, 永不回流)
+
+feat/video-engine 引入文生视频引擎 (Wan2.2 T2V A14B via mlx-gen, 设计
+docs/video-generation-engine-spec.md). 这是 fmlx 与上游的有意分化,
+不向上游 PR. 对上游同源文件的补丁面 (cherry-pick 撞冲突时参考):
+
+- model_discovery.py: ModelType/EngineType Literal + model_index.json
+  识别分支 + _register_model 视频臂与跳过过滤
+- engine_pool.py: Literal + 映射 + get_engine 入口 video 拒绝臂 +
+  _load_engine 防御臂
+- server.py: video 路由挂载 / pre-pool 400 / 默认模型 chat-capable 过滤 /
+  ModelInfo.model_type / lifespan 构造与关停 VideoJobManager
+- process_memory_enforcer.py: 视频内存租约 (acquire/set pid/release +
+  ceiling 扣减 + 动态 ceiling 加回)
+- settings.py: VideoSettings section + huggingface.disable_xet
+- admin/routes.py: valid_types/type_to_engine + 列表与删除门放宽 +
+  global-settings video 字段
+- cli.py: HF_HUB_DISABLE_XET 注入
+- exceptions.py: ModelTypeNotLoadableError
+
+全新文件 (无冲突面): omlx/video/*, omlx/api/video_models.py,
+omlx/api/video_routes.py, tests/test_video_*.py,
+scripts/video_p0_measure.py.
diff --git a/docs/video-generation-engine-spec.md b/docs/video-generation-engine-spec.md
diff --git a/omlx/admin/i18n/en.json b/omlx/admin/i18n/en.json
@@ -767,5 +767,22 @@
   "cluster.router.unknown": "unknown",
   "cluster.healthy.yes": "yes",
   "cluster.healthy.no": "no",
-  "cluster.save.failed": "Save failed"
+  "cluster.save.failed": "Save failed",
+  "settings": {
+    "video": {
+      "title": "Video Generation",
+      "enabled": "Enable video generation",
+      "enabled_desc": "Serve POST /v1/videos via the subprocess worker. Requires the video worker venv.",
+      "memory_lease": "Memory lease (GB)",
+      "memory_lease_desc": "Reserved against the memory ceiling while a job runs; co-resident LLMs throttle accordingly.",
+      "default_steps": "Default denoise steps",
+      "default_fps": "Default FPS",
+      "max_queued_jobs": "Max queued jobs",
+      "job_timeout": "Job timeout (seconds)",
+      "artifacts_max_gb": "Artifact storage cap (GB)",
+      "artifacts_max_gb_desc": "Oldest video files are purged beyond this; job records are kept.",
+      "worker_python": "Worker python path",
+      "worker_python_desc": "Python of the isolated video venv. Empty = default path."
+    }
+  }
 }
diff --git a/omlx/admin/i18n/ru.json b/omlx/admin/i18n/ru.json
@@ -742,5 +742,22 @@
   "cluster.router.unknown": "неизвестно",
   "cluster.healthy.yes": "да",
   "cluster.healthy.no": "нет",
-  "cluster.save.failed": "Не удалось сохранить"
+  "cluster.save.failed": "Не удалось сохранить",
+  "settings": {
+    "video": {
+      "title": "Генерация видео",
+      "enabled": "Включить генерацию видео",
+      "enabled_desc": "Обслуживать POST /v1/videos через подпроцесс-воркер. Требуется venv видео-воркера.",
+      "memory_lease": "Резерв памяти (ГБ)",
+      "memory_lease_desc": "Резервируется из лимита памяти на время задачи; LLM соответственно замедляются.",
+      "default_steps": "Шаги диффузии по умолчанию",
+      "default_fps": "FPS по умолчанию",
+      "max_queued_jobs": "Макс. задач в очереди",
+      "job_timeout": "Таймаут задачи (сек)",
+      "artifacts_max_gb": "Лимит хранения (ГБ)",
+      "artifacts_max_gb_desc": "Старые видеофайлы удаляются сверх лимита; записи задач сохраняются.",
+      "worker_python": "Путь к python воркера",
+      "worker_python_desc": "Python изолированного видео-venv. Пусто = путь по умолчанию."
+    }
+  }
 }
diff --git a/omlx/admin/i18n/zh.json b/omlx/admin/i18n/zh.json
@@ -765,5 +765,22 @@
   "cluster.router.unknown": "未知",
   "cluster.healthy.yes": "是",
   "cluster.healthy.no": "否",
-  "cluster.save.failed": "保存失败"
+  "cluster.save.failed": "保存失败",
+  "settings": {
+    "video": {
+      "title": "视频生成",
+      "enabled": "启用视频生成",
+      "enabled_desc": "通过子进程 worker 提供 POST /v1/videos。需要先安装视频 worker venv。",
+      "memory_lease": "内存租约 (GB)",
+      "memory_lease_desc": "任务运行期间从内存上限中预留;共驻的 LLM 会相应限流。",
+      "default_steps": "默认去噪步数",
+      "default_fps": "默认帧率",
+      "max_queued_jobs": "最大排队任务数",
+      "job_timeout": "任务超时 (秒)",
+      "artifacts_max_gb": "产物存储上限 (GB)",
+      "artifacts_max_gb_desc": "超限时清除最旧的视频文件;任务记录保留。",
+      "worker_python": "Worker python 路径",
+      "worker_python_desc": "独立视频 venv 的 python。留空用默认路径。"
+    }
+  }
 }
diff --git a/omlx/admin/routes.py b/omlx/admin/routes.py
@@ -281,6 +281,21 @@ class GlobalSettingsRequest(BaseModel):
     # Idle timeout settings. null disables the global fallback.
     idle_timeout_seconds: int | None = Field(default=None, ge=60)
 
+    # Video generation settings (docs/video-generation-engine-spec.md 4.5)
+    video_enabled: bool | None = None
+    video_worker_python: str | None = None
+    video_memory_lease_gb: float | None = Field(default=None, gt=0)
+    video_max_queued_jobs: int | None = Field(default=None, ge=1)
+    video_job_timeout_seconds: int | None = Field(default=None, ge=60)
+    video_progress_stall_timeout_seconds: int | None = Field(default=None, ge=30)
+    video_default_steps: int | None = Field(default=None, ge=1)
+    video_default_fps: int | None = Field(default=None, ge=1)
+    video_max_frames: int | None = Field(default=None, ge=5)
+    video_max_steps: int | None = Field(default=None, ge=1)
+    video_max_pixels_per_frame: int | None = Field(default=None, ge=256)
+    video_artifacts_max_count: int | None = Field(default=None, ge=1)
+    video_artifacts_max_gb: float | None = Field(default=None, gt=0)
+
     # Auth settings
     api_key: str | None = None
     skip_api_key_verification: bool | None = None
@@ -1857,7 +1872,7 @@ async def update_model_settings(
                     )
         current_settings.model_alias = alias_value
     if "model_type_override" in sent:
-        valid_types = {"llm", "vlm", "embedding", "reranker", "audio_stt", "audio_tts", "audio_sts"}
+        valid_types = {"llm", "vlm", "embedding", "reranker", "audio_stt", "audio_tts", "audio_sts", "video"}
         # Treat empty string as None (auto-detect)
         override_value = request.model_type_override or None
         if override_value is not None and override_value not in valid_types:
@@ -1875,6 +1890,7 @@ async def update_model_settings(
             "audio_stt": "audio_stt",
             "audio_tts": "audio_tts",
             "audio_sts": "audio_sts",
+            "video": "video",
         }
         if override_value:
             entry.model_type = override_value
@@ -2849,6 +2865,7 @@ async def get_global_settings(is_admin: bool = Depends(require_admin)):
         "idle_timeout": {
             "idle_timeout_seconds": global_settings.idle_timeout.idle_timeout_seconds,
         },
+        "video": global_settings.video.to_dict(),
     }
 
 
@@ -3268,6 +3285,30 @@ async def update_global_settings(
         else:
             logger.info("Idle timeout disabled")
 
+    # Apply video settings (Live for caps/timeouts; enabled flips per-request
+    # gating immediately because handlers read settings.video each call.
+    # worker_python/memory_lease affect the NEXT job dispatch.)
+    _video_fields = {
+        "video_enabled": "enabled",
+        "video_worker_python": "worker_python",
+        "video_memory_lease_gb": "memory_lease_gb",
+        "video_max_queued_jobs": "max_queued_jobs",
+        "video_job_timeout_seconds": "job_timeout_seconds",
+        "video_progress_stall_timeout_seconds": "progress_stall_timeout_seconds",
+        "video_default_steps": "default_steps",
+        "video_default_fps": "default_fps",
+        "video_max_frames": "max_frames",
+        "video_max_steps": "max_steps",
+        "video_max_pixels_per_frame": "max_pixels_per_frame",
+        "video_artifacts_max_count": "artifacts_max_count",
+        "video_artifacts_max_gb": "artifacts_max_gb",
+    }
+    for req_field, attr in _video_fields.items():
+        value = getattr(request, req_field, None)
+        if value is not None:
+            setattr(global_settings.video, attr, value)
+            runtime_applied.append(req_field)
+
     # Apply auth settings (API key change)
     if request.api_key is not None:
         from ..server import _server_state
@@ -4465,7 +4506,7 @@ async def list_hf_models(is_admin: bool = Depends(require_admin)):
 
     model_dirs = global_settings.model.get_model_dirs(global_settings.base_path)
 
-    from ..model_discovery import _resolve_hf_cache_entry
+    from ..model_discovery import _is_model_dir, _resolve_hf_cache_entry
 
     def _add_model(model_path: Path, model_name: str) -> None:
         if model_name in seen_names:
@@ -4492,23 +4533,25 @@ def _add_model(model_path: Path, model_name: str) -> None:
             if not subdir.is_dir() or subdir.name.startswith("."):
                 continue
 
-            if (subdir / "config.json").exists():
+            # _is_model_dir accepts config.json or model_index.json roots
+            # (diffusers-layout video models) and excludes adapters.
+            if _is_model_dir(subdir):
                 # Level 1: direct model folder
                 _add_model(subdir, subdir.name)
             else:
                 # HF Hub cache entry: models--Org--Name/snapshots/<hash>/
                 hf_resolved = _resolve_hf_cache_entry(subdir)
                 if hf_resolved is not None:
                     snapshot_path, model_name = hf_resolved
-                    if (snapshot_path / "config.json").exists():
+                    if _is_model_dir(snapshot_path):
                         _add_model(snapshot_path, model_name)
                     continue
 
                 # Level 2: organization folder — scan children
                 for child in sorted(subdir.iterdir()):
                     if not child.is_dir() or child.name.startswith("."):
                         continue
-                    if (child / "config.json").exists():
+                    if _is_model_dir(child):
                         _add_model(child, child.name)
 
     return {"models": models}
@@ -4528,14 +4571,18 @@ async def delete_hf_model(
 
     model_dirs = global_settings.model.get_model_dirs(global_settings.base_path)
 
-    # Search for model across all directories in both flat and org-folder layouts
+    # Search for model across all directories in both flat and org-folder
+    # layouts. _is_model_dir accepts config.json or model_index.json roots
+    # (diffusers-layout video models must be deletable too).
+    from ..model_discovery import _is_model_dir
+
     model_path = None
     parent_model_dir = None
     for model_dir in model_dirs:
         if not model_dir.exists():
             continue
         candidate = model_dir / model_name
-        if candidate.is_dir() and (candidate / "config.json").exists():
+        if candidate.is_dir() and _is_model_dir(candidate):
             model_path = candidate
             parent_model_dir = model_dir
             break
@@ -4544,7 +4591,7 @@ async def delete_hf_model(
             if not subdir.is_dir() or subdir.name.startswith("."):
                 continue
             candidate = subdir / model_name
-            if candidate.is_dir() and (candidate / "config.json").exists():
+            if candidate.is_dir() and _is_model_dir(candidate):
                 model_path = candidate
                 parent_model_dir = model_dir
                 break

diff --git a/omlx/admin/static/js/dashboard.js b/omlx/admin/static/js/dashboard.js
@@ -44,6 +44,7 @@
                 integrations: { copilot_model: null, codex_model: null, opencode_model: null, openclaw_model: null, pi_model: null, openclaw_tools_profile: 'full' },
                 ui: { language: 'en' },
                 idle_timeout: { idle_timeout_seconds: null },
+                video: { enabled: false, worker_python: '', memory_lease_gb: 36, max_queued_jobs: 4, job_timeout_seconds: 7200, progress_stall_timeout_seconds: 600, default_steps: 20, default_fps: 16, max_frames: 121, max_steps: 50, max_pixels_per_frame: 921600, artifacts_max_count: 50, artifacts_max_gb: 50 },
                 system: { total_memory_bytes: 0, total_memory: '', auto_model_memory: '', ssd_total_bytes: 0, ssd_total: '' },
             },
 
@@ -781,6 +782,7 @@
                             claude_code: { ...this.globalSettings.claude_code, ...data.claude_code },
                             integrations: { ...this.globalSettings.integrations, ...data.integrations },
                             idle_timeout: { ...this.globalSettings.idle_timeout, ...data.idle_timeout },
+                            video: { ...this.globalSettings.video, ...data.video },
                             system: { ...this.globalSettings.system, ...data.system },
                         };
                         this.globalSettings.ui = data.ui || { language: 'en' };
@@ -884,6 +886,14 @@
                             ...(this.globalSettings.auth.api_key ? { api_key: this.globalSettings.auth.api_key } : {}),
                             skip_api_key_verification: this.globalSettings.auth.skip_api_key_verification,
                             idle_timeout_seconds: this.globalSettings.idle_timeout?.idle_timeout_seconds ?? null,
+                            video_enabled: this.globalSettings.video?.enabled ?? null,
+                            video_worker_python: this.globalSettings.video?.worker_python || null,
+                            video_memory_lease_gb: this.globalSettings.video?.memory_lease_gb ?? null,
+                            video_max_queued_jobs: this.globalSettings.video?.max_queued_jobs ?? null,
+                            video_job_timeout_seconds: this.globalSettings.video?.job_timeout_seconds ?? null,
+                            video_default_steps: this.globalSettings.video?.default_steps ?? null,
+                            video_default_fps: this.globalSettings.video?.default_fps ?? null,
+                            video_artifacts_max_gb: this.globalSettings.video?.artifacts_max_gb ?? null,
                         }),
                     });
 

diff --git a/omlx/admin/templates/dashboard/_modal_model_settings.html b/omlx/admin/templates/dashboard/_modal_model_settings.html
@@ -277,6 +277,7 @@ <h3 class="text-xs font-bold uppercase tracking-widest text-neutral-400 mb-5">{{
                                         <option value="audio_stt">Audio STT</option>
                                         <option value="audio_tts">Audio TTS</option>
                                         <option value="audio_sts">Audio STS</option>
+                                        <option value="video">Video</option>
                                     </select>
                                 </div>
                                 <div x-show="reasoningParsers.length > 0">