diff --git a/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V4_1.mdx b/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V4_1.mdx
index 1b24b6d6f..61da2cc29 100644
--- a/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V4_1.mdx
+++ b/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V4_1.mdx
@@ -192,3 +192,15 @@ Prefill/decode disaggregation is validated token-identical against a single serv
 One deployment note: Mooncake needs the RDMA fabric visible inside the container, so launch with `--device /dev/infiniband:/dev/infiniband --cap-add IPC_LOCK --ulimit memlock=-1`. Without it Mooncake selects its NVLink transport, which only serves buffers from its own allocator and fails with `Requested address ... not found`. If you hit that, force TCP with `MOONCAKE_PROTOCOL=tcp` and `MC_FORCE_TCP=1` — the Playground's Mooncake option sets both.
 
 PD and speculative decoding cannot be combined.
+
+### 3.5 HiCache (Hierarchical KV Caching)
+
+HiCache extends RadixAttention with a hierarchy of KV cache tiers, significantly expanding effective context capacity for long-context and multi-turn scenarios.
+
+To enable HiCache, open the **HiCache** card in the [Playground above](#playground) and flip **Enable**: the Playground emits `--enable-hierarchical-cache` on top of the recipe's flags, and cold KV pages spill to CPU pinned memory (L2, GPU + CPU) instead of being dropped from the GPU pool. The host pool is sized by ratio (`--hicache-ratio 2`), not by a fixed `--hicache-size`.
+
+The Write policy knob controls the GPU → CPU write and defaults to `write_through` (the upstream default): every page is mirrored to the CPU tier as it is written. `write_through_selective` backs up only hot data and `write_back` defers the copy to eviction, trading cache freshness for host-side I/O.
+
+The card is not offered on MI350X: the ROCm recipes run `--disable-radix-cache`, and the server rejects that alongside `--enable-hierarchical-cache`.
+
+Only the L2 tier is exposed here. For the storage (L3) tier and the canonical flag set, see the [HiCache best-practices recipe](../../../docs/advanced_features/hicache_best_practices) and the [HiCache documentation](../../../docs/advanced_features/hicache).
diff --git a/docs/src/snippets/configs/deepseek-ai/deepseek-v4_1.jsx b/docs/src/snippets/configs/deepseek-ai/deepseek-v4_1.jsx
index e2e1247c3..405ce24bd 100644
--- a/docs/src/snippets/configs/deepseek-ai/deepseek-v4_1.jsx
+++ b/docs/src/snippets/configs/deepseek-ai/deepseek-v4_1.jsx
@@ -114,6 +114,19 @@ export const config = {
       },
     },
 
+    // GPU → CPU KV offload (L2 only; no storage tier). Hidden on MI350X: both
+    // ROCm cells run `--disable-radix-cache`, which the server rejects alongside
+    // `--enable-hierarchical-cache`.
+    hicache: {
+      excludesHw: ["mi350x"],
+      writePolicies: [
+        { id: "auto",                    label: "Auto" },
+        { id: "write_through",           label: "Write-through" },
+        { id: "write_back",              label: "Write-back" },
+        { id: "write_through_selective", label: "Write-through (selective)" },
+      ],
+    },
+
     flagSelects: [
       {
         id: "dsparkBlockSize",