diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index c6d06c2e1..098b41b45 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -67,12 +67,11 @@ dsr1-fp4-mi355x-atom:
       - { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
 
 dsr1-fp4-mi355x-atom-mtp:
-  image: rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511
-  model: amd/DeepSeek-R1-0528-MXFP4
+  image: rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3
+  model: amd/DeepSeek-R1-0528-MXFP4-MTP-MoEFP4
   model-prefix: dsr1
   runner: mi355x
   precision: fp4
-  # WIP framework (no customers yet)
   framework: atom
   multinode: false
   scenarios:
@@ -80,13 +79,11 @@ dsr1-fp4-mi355x-atom-mtp:
     - isl: 1024
       osl: 1024
       search-space:
-      - { tp: 4, conc-start: 4, conc-end: 256, spec-decoding: mtp }
-      - { tp: 8, conc-start: 4, conc-end: 256, spec-decoding: mtp }
+      - { tp: 4, conc-start: 4, conc-end: 1024, spec-decoding: mtp }
     - isl: 8192
       osl: 1024
       search-space:
-      #- { tp: 4, conc-start: 32, conc-end: 256, spec-decoding: mtp }
-      - { tp: 8, conc-start: 4, conc-end: 256, spec-decoding: mtp }
+      - { tp: 4, conc-start: 4, conc-end: 1024, spec-decoding: mtp }
 
 dsr1-fp8-mi300x-sglang:
   image: lmsysorg/sglang:v0.5.12-rocm700-mi30x
diff --git a/benchmarks/single_node/dsr1_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/dsr1_fp4_mi355x_atom_mtp.sh
index 1d557684e..e5bd6579e 100644
--- a/benchmarks/single_node/dsr1_fp4_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/dsr1_fp4_mi355x_atom_mtp.sh
@@ -24,23 +24,22 @@ PORT=${PORT:-8888}
 
 export OMP_NUM_THREADS=1
 
-# Calculate max-model-len based on ISL and OSL
-if [ "$ISL" = "1024" ] && [ "$OSL" = "1024" ]; then
-    CALCULATED_MAX_MODEL_LEN=""
-else
-    CALCULATED_MAX_MODEL_LEN=" --max-model-len 10240 "
-fi
-
+CALCULATED_MAX_MODEL_LEN=""
 if [ "${EVAL_ONLY}" = "true" ]; then
     setup_eval_context
     CALCULATED_MAX_MODEL_LEN=" --max-model-len $EVAL_MAX_MODEL_LEN "
 fi
 
-if [ "$EP_SIZE" -gt 1 ]; then
-  EP=" --enable-expert-parallel"
-else
-  EP=" "
-fi
+PARALLEL_ARGS=(-tp "$TP") #TP
+if [ "$DP_ATTENTION" = "true" ]; then
+    if [ "$EP_SIZE" -gt 1 ]; then #DP+EP
+        PARALLEL_ARGS=(-tp "$TP" --enable-expert-parallel --enable-dp-attention )
+    else #DP+TP
+        PARALLEL_ARGS=(-tp "$TP" --enable-dp-attention )
+    fi
+fi 
+
+SPEC_ARGS=(--method mtp --num-speculative-tokens 3 )
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -52,9 +51,9 @@ export AMDGCN_USE_BUFFER_OPS=1
 python3 -m atom.entrypoints.openai_server \
     --model $MODEL \
     --server-port $PORT \
-    -tp $TP \
-    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
-    --method mtp \
+    "${PARALLEL_ARGS[@]}" \
+    "${SPEC_ARGS[@]}" \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN \
     > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index c6ddcbe0d..de4e08a06 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3330,6 +3330,16 @@
     - "Update vLLM ROCm image from nightly-4f940896a32c9e2a0eba7f50d521bf5f6b4de458 to v0.22.0"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1624
 
+- config-keys:
+    - dsr1-fp4-mi355x-atom-mtp
+  description:
+    - "Update ATOM image to rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3"
+    - "Update model from amd/DeepSeek-R1-0528-MXFP4 to amd/DeepSeek-R1-0528-MXFP4-MTP-MoEFP4"
+    - "Switch to TP=4 only (drop TP=8 search-space); enable isl=8192 TP=4 sweep"
+    - "isl=1024/osl=1024 TP=4: +5.7% to +16.6% improvement at conc 4-64 vs prior InferenceX numbers"
+    - "isl=1024/osl=1024 TP=4: -0.6% to -1.9% at high concurrency (conc 128-256)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1629
+
 - config-keys:
     - kimik2.5-fp4-mi355x-vllm
   description: