[diffusion] feat: support loading mixed w4a8 text encoders (#36037)

docs/cookbook/diffusion/MiniMax/MiniMax-H3.mdx

@@ -958,6 +958,17 @@ linear layers use FP8 while embeddings, normalization, and the vision tower
 remain BF16. This is an approximate serve-time choice and is incompatible with
 the strict `quality="high"` deployment contract.
 
+The mixed W4A8 community encoder follows the same component-path contract:
+
+```bash Overlay
+--component-paths.text_encoder \
+  Winnougan/MiniMax-H3-INT4_Convrot_ComfyUI/qwen3vl_32b_minimax_h3-w4a8_convrot.safetensors
+```
+
+Install `comfy-kitchen>=0.2.27` and omit `--quantization`. SGLang automatically
+loads its W4A8 language linears and tensorwise INT8 embedding; the unmarked
+vision tower remains BF16.
+
 </Tab>
 
 <Tab title="Encoder scheduling">

docs/docs/sglang-diffusion/quantization.mdx

@@ -195,10 +195,10 @@ backend.
     <tr>
       <td><code>comfy-w4a8-convrot</code></td>
       <td>Safetensors with serialized <code>asym_w4a8_int8</code> layer metadata and packed weights</td>
-      <td><code>--transformer-weights-path</code></td>
-      <td>MiniMax-H3 FL2VA / Ref2VA DiTs</td>
+      <td><code>--transformer-weights-path</code> or <code>--component-paths.text_encoder</code></td>
+      <td>MiniMax-H3 FL2VA / Ref2VA DiTs and its native Qwen3-VL encoder</td>
       <td><code>comfy-kitchen&gt;=0.2.27</code></td>
-      <td>Auto-detected; omit <code>--quantization</code>. Requires SM80+ and validates packed weights, group/channel scales, and optional codebooks before model construction. TP must preserve ConvRot group boundaries; offload is supported and FSDP is not.</td>
+      <td>Auto-detected; omit <code>--quantization</code>. Requires SM80+ and validates packed weights, group/channel scales, and optional codebooks before model construction. Mixed encoder files may keep their embedding tensorwise INT8. TP must preserve ConvRot group boundaries; offload is supported and FSDP is not.</td>
     </tr>
     <tr>
       <td><code>qvg-kv</code></td>