diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index d3ef03291..14eec1583 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -486,7 +486,7 @@ dsr1-fp8-mi355x-atom-mtp:
     - { tp: 8, conc-start: 4, conc-end: 256, spec-decoding: mtp  }
 
 dsr1-fp8-mi355x-sglang-disagg:
-  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0227-2
+  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0327
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi355x-disagg
@@ -641,7 +641,7 @@ dsr1-fp8-mi355x-sglang-disagg:
 
 
 dsr1-fp8-mi355x-sglang-disagg-mtp:
-  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0227-2
+  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0327
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi355x-disagg
@@ -794,10 +794,9 @@ dsr1-fp8-mi355x-sglang-disagg-mtp:
         - "DECODE_NODES=1"
         - "DECODE_MTP_SIZE=2"
 
-
 dsr1-fp4-mi355x-sglang-disagg:
-  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0227-3
-  model: amd/DeepSeek-R1-0528-MXFP4
+  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0327
+  model: amd/DeepSeek-R1-0528-MXFP4-v2
   model-prefix: dsr1
   runner: mi355x-disagg
   precision: fp4
@@ -1003,9 +1002,10 @@ dsr1-fp4-mi355x-sglang-disagg:
         - "DECODE_NODES=1"
         - "DECODE_MTP_SIZE=0"
 
+
 dsr1-fp4-mi355x-sglang-disagg-mtp:
-  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0227-3
-  model: amd/DeepSeek-R1-0528-MXFP4
+  image: rocm/sgl-dev:sglang-0.5.9-rocm720-mi35x-mori-0327
+  model: amd/DeepSeek-R1-0528-MXFP4-v2
   model-prefix: dsr1
   runner: mi355x-disagg
   precision: fp4
diff --git a/benchmarks/multi_node/amd_utils/env.sh b/benchmarks/multi_node/amd_utils/env.sh
index 5565c5b3b..0aa2d0c20 100755
--- a/benchmarks/multi_node/amd_utils/env.sh
+++ b/benchmarks/multi_node/amd_utils/env.sh
@@ -34,7 +34,6 @@ export IBDEVICES
 export GLOO_SOCKET_IFNAME=$(ip route | grep '^default' | awk '{print $5}' | head -n 1)
 export NCCL_SOCKET_IFNAME=$(ip route | grep '^default' | awk '{print $5}' | head -n 1)
 
-set +x
 
 export NCCL_IB_HCA=$IBDEVICES
 
@@ -64,6 +63,8 @@ export MORI_MAX_DISPATCH_TOKENS_DECODE=160
 export SGLANG_MORI_DISPATCH_INTER_KERNEL_SWITCH_THRESHOLD=$((MORI_MAX_DISPATCH_TOKENS_DECODE * 2))
 
 export MORI_EP_LAUNCH_CONFIG_MODE=AUTO
+
+#TODO(billishyahao): The following IO env will be deprecated soon.
 export MORI_IO_QP_MAX_SEND_WR=16384
 export MORI_IO_QP_MAX_CQE=32768
 export MORI_IO_QP_MAX_SGE=4
@@ -89,17 +90,21 @@ $1 == "DSCP" && $2 == ":" && $NF == p {
     if [[ -n "$ND_DSCP" ]] && [[ -n "$ND_PRIO" ]]; then
         TC=$(( 4 * ND_DSCP ))
         export MORI_RDMA_SL=$ND_PRIO
+        export MORI_IO_SL=$ND_PRIO
         export MORI_RDMA_TC=$TC
-        echo "[INFO] Detected QoS config from nicctl: MORI_RDMA_TC=$MORI_RDMA_TC, MORI_RDMA_SL=$MORI_RDMA_SL"
+        export MORI_IO_TC=$TC
+        echo "[INFO] Detected QoS config from nicctl: MORI_RDMA_TC=$MORI_RDMA_TC, MORI_RDMA_SL=$MORI_RDMA_SL, MORI_IO_TC=$MORI_IO_TC, MORI_IO_SL=$MORI_IO_SL"
     else
         echo "[WARN] nicctl available but QoS data unavailable; trying hostname detection."
         # Fall back to hostname-based detection
         NODENAME=$(hostname -s)
         if [[ $NODENAME == GPU* ]] || [[ $NODENAME == smci355-ccs-aus* ]]; then
             export MORI_RDMA_TC=96
+            export MORI_IO_TC=96
             echo "[INFO] Auto-detected MORI_RDMA_TC=$MORI_RDMA_TC from hostname $NODENAME"
         elif [[ $NODENAME == mia1* ]]; then
             export MORI_RDMA_TC=104
+            export MORI_IO_TC=104
             echo "[INFO] Auto-detected MORI_RDMA_TC=$MORI_RDMA_TC from hostname $NODENAME"
         else
             echo "[INFO] Unable to detect MORI_RDMA_TC from hostname. Skipping RDMA QoS configuration."
@@ -110,9 +115,11 @@ else
     NODENAME=$(hostname -s)
     if [[ $NODENAME == GPU* ]] || [[ $NODENAME == smci355-ccs-aus* ]]; then
         export MORI_RDMA_TC=96
+        export MORI_IO_TC=96
         echo "[INFO] Auto-detected MORI_RDMA_TC=$MORI_RDMA_TC from hostname $NODENAME"
     elif [[ $NODENAME == mia1* ]]; then
         export MORI_RDMA_TC=104
+        export MORI_IO_TC=104
         echo "[INFO] Auto-detected MORI_RDMA_TC=$MORI_RDMA_TC from hostname $NODENAME"
     else
         echo "[INFO] nicctl not found and unable to detect from hostname. Skipping RDMA QoS configuration."
@@ -124,3 +131,4 @@ fi
 export PYTHONPATH=/sgl-workspace/aiter:${PYTHONPATH}
 
 
+set +x
diff --git a/benchmarks/multi_node/amd_utils/models.yaml b/benchmarks/multi_node/amd_utils/models.yaml
index 2bbdd91d6..eed59bdab 100644
--- a/benchmarks/multi_node/amd_utils/models.yaml
+++ b/benchmarks/multi_node/amd_utils/models.yaml
@@ -38,7 +38,7 @@
 #         cuda_graph_bs_range: str
 
 DeepSeek-V3:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -69,7 +69,7 @@ DeepSeek-V3:
       cuda_graph_bs_range: "1-128"
 
 DeepSeek-V3-0324:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -100,7 +100,7 @@ DeepSeek-V3-0324:
       cuda_graph_bs_range: "1-128"
 
 DeepSeek-R1:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -131,7 +131,7 @@ DeepSeek-R1:
       cuda_graph_bs_range: "1-128"
 
 DeepSeek-R1-0528:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -162,7 +162,7 @@ DeepSeek-R1-0528:
       cuda_graph_bs_range: "1-128"
 
 DeepSeek-R1-0528-MXFP4-Preview:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -193,7 +193,7 @@ DeepSeek-R1-0528-MXFP4-Preview:
       cuda_graph_bs_range: "1-128"
 
 DeepSeek-R1-0528-MXFP4:
-  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600 --ep-dispatch-algorithm fake --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
   mtp_flags: "--speculative-algorithm NEXTN --speculative-eagle-topk 1"
   dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
   prefill:
@@ -222,3 +222,34 @@ DeepSeek-R1-0528-MXFP4:
       max_running_requests: 128
       chunked_prefill_size: 262144
       cuda_graph_bs_range: "1-128"
+
+DeepSeek-R1-0528-MXFP4-v2:
+  base_flags: "--decode-log-interval 1000 --log-level warning --watchdog-timeout 3600  --load-balance-method round_robin --kv-cache-dtype fp8_e4m3 --attention-backend aiter --disaggregation-transfer-backend mori"
+  mtp_flags: "--speculative-draft-model-path SGLang/DeepSeek-R1-NextN --speculative-algorithm NEXTN --speculative-eagle-topk 1 --speculative-attention-mode decode "
+  dp_flags: "--moe-a2a-backend mori --deepep-mode normal --enable-dp-attention --moe-dense-tp-size 1 --enable-dp-lm-head"
+  prefill:
+    mem_fraction_static: 0.8
+    disable_radix_cache: true
+    dp:
+      max_running_requests: 24
+      chunked_prefill_size: "MORI_MAX_DISPATCH_TOKENS_PREFILL * PREFILL_TP_SIZE"
+      cuda_graph_bs: "1 2 3"
+    no_dp:
+      max_running_requests: 128
+      chunked_prefill_size: 16384
+      cuda_graph_bs_range: "1-128"
+  decode:
+    mem_fraction_static: 0.85
+    prefill_round_robin_balance: true
+    dp:
+      max_running_requests: 4096
+      chunked_prefill_size: "MORI_MAX_DISPATCH_TOKENS_DECODE * DECODE_TP_SIZE"
+      cuda_graph_bs_range: "1-160"
+    ep_only:
+      max_running_requests: 256
+      chunked_prefill_size: 262144
+      cuda_graph_bs_range: "1-256"
+    no_dp:
+      max_running_requests: 128
+      chunked_prefill_size: 262144
+      cuda_graph_bs_range: "1-128"
diff --git a/benchmarks/multi_node/amd_utils/server.sh b/benchmarks/multi_node/amd_utils/server.sh
index 7f174b760..7340ef51c 100755
--- a/benchmarks/multi_node/amd_utils/server.sh
+++ b/benchmarks/multi_node/amd_utils/server.sh
@@ -187,18 +187,8 @@ else
     decode_max_running_requests=$DECODE_MAX_RUNNING_REQUESTS_NO_DP
 fi
 
-# Use Decode configuration to configure different TP/DP size between P and D
-PREFILL_DECODE_DIFFERENT_TP=""
-if [[ "$PREFILL_ENABLE_DP" != "$DECODE_ENABLE_DP" ]]; then
-    if [[ "$DECODE_ENABLE_DP" == "true" ]]; then
-        PREFILL_DECODE_DIFFERENT_TP="--disaggregation-decode-tp ${DECODE_TP_SIZE} --disaggregation-decode-dp ${DECODE_TP_SIZE}"
-    else
-        PREFILL_DECODE_DIFFERENT_TP="--disaggregation-decode-tp ${DECODE_TP_SIZE} --disaggregation-decode-dp 1"
-    fi
-fi
-
 # Build the composed config strings (equivalent to the old MODEL_PREFILL_CONFIGS / MODEL_DECODE_CONFIGS)
-PREFILL_MODE_FLAGS="--mem-fraction-static ${PREFILL_MEM_FRACTION_STATIC} --max-running-requests ${prefill_max_running_requests} --chunked-prefill-size ${prefill_chunked_prefill_size} --cuda-graph-bs ${prefill_cuda_graph_bs[*]} ${PREFILL_DECODE_DIFFERENT_TP}"
+PREFILL_MODE_FLAGS="--mem-fraction-static ${PREFILL_MEM_FRACTION_STATIC} --max-running-requests ${prefill_max_running_requests} --chunked-prefill-size ${prefill_chunked_prefill_size} --cuda-graph-bs ${prefill_cuda_graph_bs[*]} "
 if [[ "$PREFILL_DISABLE_RADIX_CACHE" == "True" ]] || [[ "$PREFILL_DISABLE_RADIX_CACHE" == "true" ]]; then
     PREFILL_MODE_FLAGS="$PREFILL_MODE_FLAGS --disable-radix-cache"
 fi
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 3dbc5eccc..1cd22211a 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1213,3 +1213,13 @@
     - "Uses nvidia/GLM-5-NVFP4 model with modelopt_fp4 quantization"
     - "Image: lmsysorg/sglang:nightly-dev-cu13-20260328-a27651d5"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/973
+
+- config-keys:
+    - dsr1-fp4-mi355x-sglang-disagg
+    - dsr1-fp4-mi355x-sglang-disagg-mtp
+  description:
+    - "Bump SGL mori image to March 27"
+    - "Add more low latency sweep configs"
+    - "Enable v2 mxfp4 DSR1 0528 model"
+    - "Enable fp4 disp feature on mori"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/983