diff --git a/docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx b/docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx
index fd57a7fd5..499df1e1a 100644
--- a/docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx
+++ b/docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx
@@ -29,7 +29,8 @@ Then run the **Python** output of the command panel below in that environment.
 <Tab title="Docker">
 
 ```bash Command
-docker pull lmsysorg/sglang:latest
+docker pull lmsysorg/sglang:latest                                  # NVIDIA (CUDA)
+docker pull lmsysorg/sglang-rocm:v0.5.17-rocm720-mi35x-20260817     # AMD MI350X / MI355X (ROCm)
 ```
 
 For how to launch the image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker). Substitute the inner `sglang serve ...` with what the command generator below produces.
@@ -151,7 +152,7 @@ Speculation: DSPARK holds block size + 1 (= 8) intermediate states per request 
 | GB200 4×4 | TP16/DCP16 | MNNVL auto-detected |
 | H200 2×8 (4×8 on Unified High-Throughput) | TP16/EP16 + symm-mem, Marlin + FlashMLA; High-Throughput widens to TP32/EP32 over 4 nodes at mem-frac 0.90 with `extra_buffer_lazy` | same block on every node; export the cross-node NIC (`GLOO_SOCKET_IFNAME` / `NCCL_SOCKET_IFNAME`, `SGLANG_HOST_IP`); keep `NCCL_MNNVL_ENABLE=1 NCCL_CUMEM_ENABLE=1` |
 | H100 4×8 | TP32/EP32, Marlin + FlashMLA | SM90a build of the K3 image; pin NCCL/Gloo to the same NIC on all nodes; least post-weight headroom (80 GB) |
-| MI350X/MI355X 1×8 | TP8 ROCm/AITER | AITER A8W4 FlyDSL MoE, Triton attention, graph bs up to 256, fp8 kvcache; DSPARK supported |
+| MI350X/MI355X 1×8 | TP8 ROCm/AITER | AITER A8W4 FlyDSL MoE, Triton attention (`SGLANG_MLA_DECODE_TUNE=1` for gfx950 MLA decode geometry), graph bs up to 256, fp8 kvcache; DSPARK supported |
 
 **DCP notes** — the DCP cells are Balanced and High-Throughput on every Blackwell platform, in both the `Unified` and `Decode` roles:
 
diff --git a/docs/src/snippets/configs/moonshotai/kimi-k3.jsx b/docs/src/snippets/configs/moonshotai/kimi-k3.jsx
index 72783e08d..601e1508d 100644
--- a/docs/src/snippets/configs/moonshotai/kimi-k3.jsx
+++ b/docs/src/snippets/configs/moonshotai/kimi-k3.jsx
@@ -234,7 +234,9 @@ export const config = {
       title: "Spec Decode",
       default: "dspark",
       options: [
-        { id: "none", label: "Non-Spec" },
+        { id: "none", label: "Non-Spec",
+          env: (s) => (["mi350x", "mi355x"].includes(s.hw) ? ["SGLANG_MLA_DECODE_TUNE=1"] : []),
+        },
         {
           id: "dspark",
           label: "DSPARK",
@@ -411,8 +413,8 @@ export const config = {
     gb300:  "lmsysorg/sglang:kimi-k3",
     b200:   "lmsysorg/sglang:kimi-k3",
     gb200:  "lmsysorg/sglang:kimi-k3",
-    mi350x: "lmsysorg/sglang-rocm:rocm720-mi35x-k3-20260727",
-    mi355x: "lmsysorg/sglang-rocm:rocm720-mi35x-k3-20260727",
+    mi350x: "lmsysorg/sglang-rocm:v0.5.17-rocm720-mi35x-20260817",
+    mi355x: "lmsysorg/sglang-rocm:v0.5.17-rocm720-mi35x-20260817",
     // NVFP4 needs a build with sgl-project/sglang#35077; the purpose-built dev
     // image is cut from that PR's head (CUDA 13).
     "b300|nvfp4":  "lmsysorg/sglang:dev-dev-kimi-k3-nvfp4",