Cookbook for QAT (#27396)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

docs_new/cookbook/autoregressive/Google/Gemma4.mdx

@@ -113,6 +113,7 @@ For other installation methods, please refer to the [official SGLang installatio
 - **Attention backend on Blackwell (B200/sm100)**: SGLang defaults to the `trtllm_mha` backend on sm100, which is fastest for text but applies *causal* attention to image tokens. For multimodal (image) workloads on B200, pass `--attention-backend triton` to restore bidirectional image-token attention and full vision quality. Text-only and audio workloads are unaffected by the default.
 - For the 26B-A4B MoE model, consider `--tp 2` for high-throughput workloads.
 - **Speculative Decoding (MTP)**: Each Gemma 4 variant ships with a paired `*-assistant` draft model that enables NEXTN multi-token prediction. Enable it via the selector above, or pass `--speculative-algorithm NEXTN --speculative-draft-model-path google/gemma-4-<variant>-it-assistant --speculative-num-steps 5 --speculative-num-draft-tokens 6 --speculative-eagle-topk 1`. MTP can significantly reduce latency for interactive use cases. The 26B-A4B MoE model requires `--tp 2` when MTP is enabled.
+- **QAT checkpoints**: Toggle **Checkpoint → QAT** in the selector to target the `qat-q4_0-unquantized` releases. These keep bf16 weights, so memory and TP requirements match the standard checkpoints, and each has a matching `*-qat-q4_0-unquantized-assistant` draft model for MTP.
 - Hardware requirements:
 
 <table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>

docs_new/src/snippets/autoregressive/gemma4-deployment.jsx

@@ -11,6 +11,14 @@ export const Gemma4Deployment = () => {
         { id: '26b-a4b', label: '26B-A4B (MoE)', default: false },
       ]
     },
+    checkpoint: {
+      name: 'checkpoint',
+      title: 'Checkpoint',
+      items: [
+        { id: 'standard', label: 'Standard', subtitle: 'BF16', default: true },
+        { id: 'qat', label: 'QAT', subtitle: 'q4_0-unquantized', default: false },
+      ]
+    },
     hardware: {
       name: 'hardware',
       title: 'Hardware Platform',
@@ -90,12 +98,17 @@ export const Gemma4Deployment = () => {
       '26b-a4b': 'google/gemma-4-26B-A4B-it',
     };
 
+    // QAT releases keep bf16 weights (q4_0-unquantized), so the only change is
+    // the model-path suffix; TP/memory requirements match the standard checkpoints.
+    const qatSuffix = values.checkpoint === 'qat' ? '-qat-q4_0-unquantized' : '';
+    const modelPath = `${modelNames[modelSize]}${qatSuffix}`;
+
     const mtpEnabled = values.speculative === 'enabled';
     if (mtpEnabled && modelSize === '26b-a4b' && hardware !== 'mi300x') {
       tp = 2;
     }
 
-    let cmd = `sglang serve --model-path ${modelNames[modelSize]}`;
+    let cmd = `sglang serve --model-path ${modelPath}`;
     if (tp > 1) {
       cmd += ` \\\n  --tp ${tp}`;
     }
@@ -110,7 +123,7 @@ export const Gemma4Deployment = () => {
 
     if (mtpEnabled) {
       cmd += ` \\\n  --speculative-algorithm NEXTN`;
-      cmd += ` \\\n  --speculative-draft-model-path ${modelNames[modelSize]}-assistant`;
+      cmd += ` \\\n  --speculative-draft-model-path ${modelPath}-assistant`;
       cmd += ` \\\n  --speculative-num-steps 5`;
       cmd += ` \\\n  --speculative-num-draft-tokens 6`;
       cmd += ` \\\n  --speculative-eagle-topk 1`;