diff --git a/benchmarks/multi_node/amd_utils/models_vllm.yaml b/benchmarks/multi_node/amd_utils/models_vllm.yaml
index 13456c2dcb..6d2cfb6deb 100644
--- a/benchmarks/multi_node/amd_utils/models_vllm.yaml
+++ b/benchmarks/multi_node/amd_utils/models_vllm.yaml
@@ -59,3 +59,27 @@ MiniMax-M3-MXFP8:
   decode_flags: "--tensor-parallel-size 8 --block-size 128 --language-model-only --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --no-enable-prefix-caching --gpu-memory-utilization 0.90 --tool-call-parser minimax_m3 --reasoning-parser minimax_m3 --enable-auto-tool-choice"
   env: "VLLM_USE_V1=1 VLLM_ROCM_USE_AITER=1 VLLM_USE_BREAKABLE_CUDAGRAPH=0 VLLM_ENGINE_READY_TIMEOUT_S=3600"
   hf_dir: "models--MiniMaxAI--MiniMax-M3-MXFP8"
+
+DeepSeek-V4-Pro:
+  # DeepSeek-V4-Pro is mixed-precision FP4+FP8 (FP4 MoE expert weights dominate
+  # the ~960 GB footprint; FP8 on attention/norm/router; FP8 KV cache at runtime).
+  # InferenceX classifies this as the fp4 variant.
+  #
+  # Serving flags reuse the validated single-node MI355X recipe
+  # (benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_vllm.sh, from
+  # vllm-project/recipes#433) so the per-node engine config is identical to the
+  # known-good aggregated run; disaggregation only adds the MoRIIO kv-transfer
+  # role (injected by server_vllm.sh). Each P/D worker is a full TP=8 node, EP=1
+  # — matching the aggregated recipe, which runs DSv4 on TP=8 without expert
+  # parallelism. DEP decode is a follow-up.
+  #
+  # --moe-backend triton_unfused is REQUIRED for the FP4 MoE expert weight format;
+  # the auto backend doesn't register the FP4 scale params and safetensors load
+  # raises KeyError. --enforce-eager (no CUDA graphs) keeps the first disagg recipe
+  # robust against cudagraph/MoRIIO-hook interactions; FULL/PIECEWISE capture is a
+  # follow-up. --async-scheduling is intentionally omitted (not used by the kimi /
+  # minimax vllm-disagg recipes).
+  prefill_flags: "--tensor-parallel-size 8 --distributed-executor-backend mp --kv-cache-dtype fp8 --moe-backend triton_unfused --tokenizer-mode deepseek_v4 --reasoning-parser deepseek_v4 --no-enable-prefix-caching --gpu-memory-utilization 0.9 --max-num-batched-tokens 8192 --enforce-eager"
+  decode_flags: "--tensor-parallel-size 8 --distributed-executor-backend mp --kv-cache-dtype fp8 --moe-backend triton_unfused --tokenizer-mode deepseek_v4 --reasoning-parser deepseek_v4 --no-enable-prefix-caching --gpu-memory-utilization 0.9 --max-num-batched-tokens 8192 --enforce-eager"
+  env: "VLLM_USE_V1=1 VLLM_ROCM_USE_AITER=1 VLLM_ENGINE_READY_TIMEOUT_S=3600"
+  hf_dir: "models--deepseek-ai--DeepSeek-V4-Pro"
diff --git a/benchmarks/multi_node/dsv4_fp4_mi355x_vllm-disagg.sh b/benchmarks/multi_node/dsv4_fp4_mi355x_vllm-disagg.sh
new file mode 100755
index 0000000000..e47cc153a1
--- /dev/null
+++ b/benchmarks/multi_node/dsv4_fp4_mi355x_vllm-disagg.sh
@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+
+# DeepSeek-V4-Pro disaggregated prefill/decode on MI355X via vLLM + MoRI-IO.
+# Thin, model-agnostic launcher: all serving flags / env live in the
+# DeepSeek-V4-Pro entry of amd_utils/models_vllm.yaml, and topology (P/D node
+# counts, TP/EP) comes from amd-master.yaml. Identical in shape to the kimi /
+# minimax vllm-disagg wrappers; only the model differs.
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    CONC_LIST \
+    ISL \
+    OSL \
+    IMAGE \
+    SPEC_DECODING \
+    MODEL_PATH \
+    PREFILL_NUM_WORKERS \
+    PREFILL_TP \
+    PREFILL_EP \
+    PREFILL_DP_ATTN \
+    DECODE_NUM_WORKERS \
+    DECODE_TP \
+    DECODE_EP \
+    DECODE_DP_ATTN \
+    PREFILL_NODES \
+    DECODE_NODES \
+    RANDOM_RANGE_RATIO \
+    FRAMEWORK
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+set -x
+
+cd "$GITHUB_WORKSPACE/benchmarks/multi_node/amd_utils" || exit 1
+
+export TIME_LIMIT="08:00:00"
+export MODEL_PATH=$MODEL_PATH
+export MODEL_NAME=$MODEL_NAME
+export CONTAINER_IMAGE=$IMAGE
+
+# Same EP/DP booleans as kimik2.5_fp4_mi355x_vllm-disagg.sh → amd_utils/submit.sh
+if [[ "${PREFILL_EP:-1}" -eq 1 ]]; then
+    export PREFILL_ENABLE_EP=false
+else
+    export PREFILL_ENABLE_EP=true
+fi
+
+if [[ "$PREFILL_DP_ATTN" == "true" ]]; then
+    export PREFILL_ENABLE_DP=true
+else
+    export PREFILL_ENABLE_DP=false
+fi
+
+if [[ "${DECODE_EP:-1}" -eq 1 ]]; then
+    export DECODE_ENABLE_EP=false
+else
+    export DECODE_ENABLE_EP=true
+fi
+
+if [[ "$DECODE_DP_ATTN" == "true" ]]; then
+    export DECODE_ENABLE_DP=true
+else
+    export DECODE_ENABLE_DP=false
+fi
+
+# Parameter order matches SGLang disagg submit.sh; arg 16 is optional NODELIST.
+JOB_ID=$(bash ./submit.sh $PREFILL_NODES \
+    $PREFILL_NUM_WORKERS \
+    $DECODE_NODES \
+    $DECODE_NUM_WORKERS \
+    $ISL $OSL "${CONC_LIST// /x}" inf \
+    ${PREFILL_ENABLE_EP} ${PREFILL_ENABLE_DP} \
+    ${DECODE_ENABLE_EP} ${DECODE_ENABLE_DP} \
+    ${PREFILL_TP} ${DECODE_TP} \
+    ${RANDOM_RANGE_RATIO} \
+    "${NODELIST:-}")
+
+if [[ $? -ne 0 ]]; then
+    echo "Failed to submit job" >&2
+    exit 1
+fi
+
+echo "$JOB_ID"
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index d3f1c70e6c..df65bf9410 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1326,6 +1326,60 @@ kimik2.5-fp4-mi355x-vllm-disagg:
           additional-settings:
           - "DECODE_NODES=2"
 
+# DeepSeek-V4-Pro disaggregated prefill/decode on MI355X via vLLM + MoRI-IO.
+# Combines the validated single-node DSv4 vLLM serving recipe
+# (dsv4-fp4-mi355x-vllm, vllm-project/recipes#433) with the vLLM-disagg
+# framework (the kimi / minimax vllm-disagg recipes). Routes to
+# benchmarks/multi_node/dsv4_fp4_mi355x_vllm-disagg.sh; per-node serving flags
+# + env live in the DeepSeek-V4-Pro entry of amd_utils/models_vllm.yaml.
+#
+# DeepSeek-V4-Pro is FP4+FP8 mixed (FP4 MoE expert weights, FP8 for the rest);
+# InferenceX classifies this as fp4 — same as dsv4-fp4-mi355x-{sglang,vllm,atom}.
+#
+# Image: latest vLLM ROCm nightly (2026-07-04). The patch-free MoRI-IO path
+# (vllm#40344) and the DSv4 model class (vllm#40871) are both long since in
+# nightlies; the release tags still trail on #40344, hence nightly.
+#
+# Topology 1P1D: each prefill/decode worker is a full TP=8 node (EP=1),
+# matching the aggregated recipe which runs DSv4 on TP=8 without expert
+# parallelism (no all2all backend needed). DEP decode + 1P2D are follow-ups
+# once the base disagg path validates.
+dsv4-fp4-mi355x-vllm-disagg:
+  image: vllm/vllm-openai-rocm:nightly-f329ce405b12623fb8b1cf1830f12e5a712523be
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: mi355x-disagg
+  precision: fp4
+  framework: vllm-disagg
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    # Smoke test: a single ISL/OSL (8k/1k) at a single concurrency (conc=32) to
+    # validate the DSv4 vLLM-disagg path (image, MoRIIO transport, serving
+    # flags, model staging) end-to-end before expanding to the full 1k1k + 8k1k
+    # conc sweep that the kimi / minimax vllm-disagg recipes run.
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # 1P1D: 1 prefill node (co-located with proxy) + 1 decode node = 2 nodes
+      - spec-decoding: "none"
+        conc-list: [ 32 ]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+          additional-settings:
+          - "PREFILL_NODES=1"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+          additional-settings:
+          - "DECODE_NODES=1"
+
 dsr1-fp4-mi355x-sglang-disagg:
   image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260519
   model: amd/DeepSeek-R1-0528-MXFP4-v2
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 320289d243..db695aea45 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4455,3 +4455,12 @@
   description:
     - "Update SGLang image from qwen3.5-fp8-h200-sglang: lmsysorg/sglang:v0.5.12-cu130 / qwen3.5-fp8-h200-sglang-mtp: lmsysorg/sglang:v0.5.12 to lmsysorg/sglang:v0.5.14-cu130"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2061
+
+- config-keys:
+    - dsv4-fp4-mi355x-vllm-disagg
+  description:
+    - "New recipe: DeepSeek-V4-Pro disaggregated prefill/decode on MI355X via vLLM + MoRI-IO, combining the validated single-node DSv4 vLLM serving recipe (dsv4-fp4-mi355x-vllm, vllm-project/recipes#433) with the existing vllm-disagg framework (MoRI-IO P/D, standalone router)."
+    - "New benchmarks/multi_node/dsv4_fp4_mi355x_vllm-disagg.sh launcher + DeepSeek-V4-Pro entry in amd_utils/models_vllm.yaml. Per-node flags reuse the aggregated recipe verbatim (--moe-backend triton_unfused for the FP4 expert format, deepseek_v4 tokenizer/reasoning parser, fp8 KV cache, --enforce-eager); the framework adds the MoRIIO kv-transfer role with the patch-free read_mode path already on main."
+    - "Image: latest vLLM ROCm nightly vllm/vllm-openai-rocm:nightly-f329ce405b12623fb8b1cf1830f12e5a712523be (2026-07-04)."
+    - "1P1D topology, TP8/EP1 prefill+decode. Smoke test: single ISL/OSL (8k/1k) at conc=32 to validate the path end-to-end before expanding to the full sweep."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2081