[diffusion] feat: load quantized H3 text encoder checkpoints (#34986)

Co-authored-by: Yiqi Yang <yangyiqi8787@gmail.com>

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

@@ -738,6 +738,29 @@ The picker exposes this option only on the B200 and B300 topologies used for
 real H3 validation runs.
 </Warning>
 
+The Qwen3-VL text encoder can be replaced independently of the DiT. To reduce
+its resident memory, point the text-encoder component at the serialized FP8
+checkpoint used in validation:
+
+```bash Command
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --model-variant fl2va \
+  --component-paths.text_encoder Qwen/Qwen3-VL-32B-Instruct-FP8 \
+  --num-gpus 4 \
+  --tp-size 2 \
+  --ulysses-degree 2 \
+  --performance-mode speed \
+  --port 30010
+```
+
+`--text-encoder-path` is accepted as a shorter alias. No separate quantization
+flag is required: SGLang reads the checkpoint's `quantization_config` and
+fails closed if the native encoder does not support that format. The language
+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.
+
 </Tab>
 
 </Tabs>

docs/docs/sglang-diffusion/api/cli.mdx

@@ -129,6 +129,12 @@ For quantized transformer checkpoints, prefer:
 - `--quantization` for online quantization (apply quantization to unquantized models at load time, activations are quantized dynamically)
 - `--quantization-ignored-layers` layer name patterns to keep unquantized (e.g. `attention.to_`)
 
+Component checkpoint paths are selected separately, so changing DiT precision
+never silently changes prompt embeddings. For a native text encoder:
+
+- `--component-paths.text_encoder {MODEL}` replaces the text-encoder checkpoint; `--text-encoder-path {MODEL}` is its shorter alias
+- Quantization metadata is auto-detected from that checkpoint. Each native encoder must explicitly support the serialized format; this is not blanket quantization support for every component, and unsupported combinations fail before weight loading.
+
 For supported realtime causal video models, `--kv-cache-quant {off|int4|int2}`
 compresses completed KV-cache chunks independently of transformer weight
 quantization. It is lossy and disabled by default.

docs/docs/sglang-diffusion/quantization.mdx

@@ -2,11 +2,12 @@
 title: "Quantization"
 tag: "approx"
 metatags:
-    description: "Configure transformer weight quantization and Quant-VideoGen causal KV-cache quantization in SGLang-Diffusion."
+    description: "Configure transformer and native text-encoder checkpoint quantization, plus Quant-VideoGen causal KV-cache quantization in SGLang-Diffusion."
 ---
 
-SGLang-Diffusion supports quantized transformer checkpoints. In most cases, keep
-the base model and the quantized transformer override separate.
+SGLang-Diffusion supports quantized transformer checkpoints and selected
+quantized native text-encoder checkpoints. Transformer and text-encoder
+precision are resolved independently.
 
 ## Quick Reference
 
@@ -17,6 +18,8 @@ Use these paths:
 - `--transformer-weights-path`: quantized transformer weights provided as a single safetensors file, a sharded safetensors directory, a local path, or a Hugging Face repo ID
 - `--quantization`: apply online quantization to unquantized models at load time (activations are quantized dynamically)
 - `--quantization-ignored-layers` layer name patterns to keep unquantized (e.g. `attention.to_`)
+- `--component-paths.text_encoder`: replace a native text encoder with a checkpoint whose `quantization_config` is auto-detected
+- `--text-encoder-path`: shorter alias for `--component-paths.text_encoder`
 - `--kv-cache-quant`: compress completed causal KV-cache chunks for supported realtime models
 
 Recommended example for pre-quantized checkpoints:
@@ -280,6 +283,27 @@ sglang generate \
 
 Each pattern is matched against the full layer prefix (e.g. `layers.0.attention.to_q`). A layer is skipped and left unquantizd if its prefix contains any of the given patterns.
 
+## MiniMax-H3 Text Encoder FP8
+
+MiniMax-H3 can load a serialized FP8 checkpoint for the language linear layers
+in its native Qwen3-VL text encoder independently of the DiT. Embeddings,
+normalization layers, and the Qwen vision tower remain in BF16.
+
+```bash Command
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --model-variant fl2va \
+  --component-paths.text_encoder Qwen/Qwen3-VL-32B-Instruct-FP8 \
+  --num-gpus 4 \
+  --port 30010
+```
+
+`--text-encoder-path` is accepted as a shorter alias. No quantization flag is
+needed: SGLang detects the checkpoint metadata and only enables formats that
+the native encoder explicitly supports. Text-encoder FP8 is approximate, is
+not enabled by default, and is rejected by MiniMax-H3's strict
+`quality="high"` deployment contract.
+
 ## Validated ModelOpt Checkpoints
 
 This section is the canonical support matrix for the thirteen published