[diffusion] cli: support component attention backend overrides (#24320)

docs/diffusion/api/cli.md

@@ -78,6 +78,7 @@ Use `sglang generate --help` and `sglang serve --help` for the full argument lis
 - `--sp-degree {N}`: sequence parallelism size
 - `--ulysses-degree {N}` and `--ring-degree {N}`: USP parallelism controls
 - `--attention-backend {BACKEND}`: attention backend for native SGLang pipelines
+- `--component-attention-backends {MAP}`: per-component attention backend overrides, for example `text_encoder=torch_sdpa,transformer=fa`
 - `--attention-backend-config {CONFIG}`: attention backend configuration
 
 ### Sampling and output
@@ -195,6 +196,28 @@ sglang serve \
 
 The component key must match the key in the model's `model_index.json`, and the path must be either a Hugging Face repo ID or a complete component directory.
 
+## Component Attention Backend Overrides
+
+Use `--component-attention-backends` when one pipeline component needs a different native attention backend from the global `--attention-backend`.
+
+```bash
+sglang generate \
+  --model-path Lightricks/LTX-2.3 \
+  --attention-backend fa \
+  --component-attention-backends text_encoder=torch_sdpa
+```
+
+The component key must match a pipeline module key such as `text_encoder`, `text_encoder_2`, `transformer`, `transformer_2`, or `connectors`. Component overrides take precedence over the global `--attention-backend` only while that component is being constructed.
+
+You can also pass dotted CLI entries:
+
+```bash
+sglang generate \
+  --model-path <MODEL_PATH_OR_ID> \
+  --component-attention-backends.text_encoder torch_sdpa \
+  --component-attention-backends.transformer fa
+```
+
 ## Diffusers Backend
 
 Use `--backend diffusers` to force vanilla diffusers pipelines when no native SGLang implementation exists or when a model requires a custom pipeline class.

docs/diffusion/performance/attention_backends.md

@@ -42,8 +42,9 @@ For SGLang-native pipelines, the CLI accepts the lowercase names of `AttentionBa
 The selection order in `runtime/layers/attention/selector.py` is:
 
 1. `global_force_attn_backend(...)` / `global_force_attn_backend_context_manager(...)`
-2. CLI `--attention-backend` (`ServerArgs.attention_backend`)
-3. Auto selection (platform capability, dtype, and installed packages)
+2. Component override from `--component-attention-backends` while that component is being constructed
+3. CLI `--attention-backend` (`ServerArgs.attention_backend`)
+4. Auto selection (platform capability, dtype, and installed packages)
 
 ## Configuration
 
@@ -122,6 +123,20 @@ sglang generate \
   --attention-backend torch_sdpa
 ```
 
+### Override one component
+
+Use component overrides when a specific module needs different attention semantics from the main transformer:
+
+```bash
+sglang generate \
+  --model-path <MODEL_PATH_OR_ID> \
+  --prompt "..." \
+  --attention-backend fa \
+  --component-attention-backends text_encoder=torch_sdpa
+```
+
+Component keys match pipeline module names from `model_index.json`, such as `text_encoder`, `text_encoder_2`, `transformer`, `transformer_2`, or `connectors`.
+
 ### Using Sliding Tile Attention (STA)
 
 ```bash