diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index ac4e276906..a1d0cb4f35 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1536,7 +1536,7 @@ dsr1-fp4-mi355x-sglang-disagg-mtp:
           - "DECODE_MTP_SIZE=1"
 
 dsv4-fp4-mi355x-sglang-agentic-hicache:
-  image: lmsysorg/sglang-rocm:v0.5.14-rocm720-mi35x-20260710
+  image: rocm/pytorch-private:sglang-rocm720-mi35x_dsv4_mlpnopad
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: cluster:mi355x-amds
@@ -1547,9 +1547,10 @@ dsv4-fp4-mi355x-sglang-agentic-hicache:
     agentic-coding:
     - dram-utilization: 0.80
       search-space:
-      - { tp: 8, kv-offloading: none, conc-list: [1, 2, 4, 8] }
-      - { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [16, 32, 48, 64] }
-      - { tp: 8, dp-attn: true, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [64] }
+      #- { tp: 8, kv-offloading: none, conc-list: [1, 2, 4, 8] }
+      #- { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [16, 32, 48, 64] }
+      #- { tp: 8, dp-attn: true, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [64] }
+      - { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [48, 64] }
 
 # MiniMax-M3 MXFP8 MI355X recipe:
 # https://github.com/vllm-project/recipes/commit/2a3728ed9892debfd767a72a58ebc90b33f186e5
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 38efdbf219..d26494f4a8 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5010,4 +5010,10 @@
     - "Add MTP speculative-decoding for the B300 vLLM AgentX recipe as a separate config-key, so the existing dsv4-fp4-b300-vllm-agentic aggregate is not re-run."
     - "dsv4-fp4-b300-vllm-agentic-mtp: MTP twins (--speculative-config {\"method\":\"mtp\",\"num_speculative_tokens\":3}) of the aggregate arms plus a new TP8 GPU-resident arm -- TP8 GPU-resident [1,2,4,6,8], TP4 GPU-resident [1,2,4,6,8,12,16,20], TP4 SimpleCPU [20,24,28,32,36,40], DEP4 [32,40,48,56], DEP8 [64,96,112,128,144,160,176,192,224]; routed via spec-decoding=mtp to dsv4_fp4_b300_vllm_mtp.sh (FULL_DECODE_ONLY cudagraph capture sizes in TOKENS = num_seqs*4)."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2258
-  
+
+- config-keys:
+    - dsv4-fp4-mi355x-sglang-agentic-hicache
+  description:
+    - "Switch image to rocm/pytorch-private:sglang-rocm720-mi35x_dsv4_mlpnopad for MLP no-pad kernel evaluation on DSv4"
+    - "Disable non-DPA, full-DPA, and HiCache sweep arms; keep only DPA no-offload conc [48, 64]"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2297
diff --git a/runners/launch_mi355x-amds.sh b/runners/launch_mi355x-amds.sh
index 75a67c1c58..4cdc314a0a 100644
--- a/runners/launch_mi355x-amds.sh
+++ b/runners/launch_mi355x-amds.sh
@@ -268,7 +268,7 @@ else
     export GPU_COUNT="${GPU_COUNT:-${TP:?TP must be set}}"
 
     set -x
-    salloc --partition=$PARTITION --gres=gpu:$GPU_COUNT --exclusive --cpus-per-task=128 --time=500 --no-shell --job-name="$RUNNER_NAME"
+    salloc --partition=$PARTITION --gres=gpu:$GPU_COUNT --exclusive --cpus-per-task=128 --time=500 --no-shell --job-name="$RUNNER_NAME" --exclude=mia1-p01-g09,mia1-p01-g11
     JOB_ID=$(squeue --name="$RUNNER_NAME" -h -o %A | head -n1)
 
     srun --jobid=$JOB_ID bash -c "docker stop \$(docker ps -a -q)"