From 9c70d22721d3bb29541bb489f495a38aac4d612d Mon Sep 17 00:00:00 2001
From: Faradawn Yang <73060648+faradawn@users.noreply.github.com>
Date: Wed, 2 Sep 2026 14:39:09 -0700
Subject: [PATCH] Update GLM-5.2 NVFP4 B200/B300 for AgentX HiCache (#35368)

---
 docs/cookbook/autoregressive/GLM/GLM-5.2.mdx | 30 ++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/docs/cookbook/autoregressive/GLM/GLM-5.2.mdx b/docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
index 47e9ec0c3..3651e2e68 100644
--- a/docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
+++ b/docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
@@ -269,3 +269,33 @@ When deploying with PD Disaggregation, the prefill node can choose to enable [La
 --cp-strategy interleave \
 ```
 With LayerSplit, the kv cache on each rank can be sharded over the CP attention group, and prefetched when necessary. This can reduce kv cache memory by up to 75%, thus increasing the throughput on prefill side.
+
+### 3.6 Agentic Long-Context with HiCache DRAM Offload (NVFP4, MTP)
+
+**B300 (TP8):**
+```bash Command
+python3 -m sglang.launch_server \
+  --model-path nvidia/GLM-5.2-NVFP4 \
+  --trust-remote-code \
+  --tp 8 \
+  --ep-size 1 \
+  --quantization modelopt_fp4 \
+  --kv-cache-dtype fp8_e4m3 \
+  --bf16-gemm-backend cutedsl \
+  --max-prefill-tokens 8192 \
+  --chunked-prefill-size 8192 \
+  --mem-fraction-static 0.85 \
+  --tool-call-parser glm47 \
+  --reasoning-parser glm45 \
+  --speculative-algorithm EAGLE \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --enable-hierarchical-cache \
+  --hicache-size 270 \
+  --hicache-write-policy write_back \
+  --hicache-io-backend direct \
+  --hicache-mem-layout page_first_direct
+```
+
+**B200 (TP8):** same command, with `--mem-fraction-static 0.83` and `--hicache-size 169`. Lower concurrency (c1/c4/c8) uses `--hicache-ratio 0.75` instead.