diff --git a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh
index 8b7d28794..ccba2f421 100644
--- a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh
+++ b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh
@@ -52,10 +52,12 @@ install_agentic_deps
 export VLLM_ROCM_AITER_MLA_ASM_PADDING=asm
 export VLLM_ROCM_USE_AITER=1
 export SAFETENSORS_FAST_GPU=1
-export VLLM_ROCM_USE_AITER_MOE_SITUV2_A8W4=1
-export AITER_SITUV2_A8W4=1
+# Route the K3 SiTU MXFP4 MoE through the FlyDSL SiTUv2 a4w4 path (fp4
+# activations). vLLM exports AITER_SITUV2_A4W4=1 from this flag at init and
+# clears any legacy AITER_SITUV2_A8W4 override; the tuned a4w4 dispatch needs
+# AITER >= v0.1.20 (ROCm/aiter#4463), otherwise FlyDSL falls back to heuristics.
+export VLLM_ROCM_USE_AITER_MOE_SITUV2=1
 export AITER_BF16_FP8_MOE_BOUND=0
-export VLLM_USE_BREAKABLE_CUDAGRAPH=0
 export AITER_QUICK_REDUCE_QUANTIZATION=INT4
 
 # MEC FW <177 has an RCCL memory reclaim issue.
@@ -110,7 +112,7 @@ case "${KV_OFFLOAD_BACKEND:-}" in
       lmcache)
     require_agentic_kv_offload_backend "$KV_OFFLOAD_BACKEND"
 
-    LMCACHE_VERSION=0.5.5.dev114+rocm7.2
+    LMCACHE_VERSION=0.5.6.dev101+rocm7.2
     LMCACHE_ROCM_INDEX="https://github.com/LMCache/LMCache/releases/expanded_assets/nightly-rocm"
 
     agentic_pip_install --quiet --no-cache-dir --no-deps \
@@ -217,7 +219,13 @@ case "$CONC" in
         GPU_MEM_UTIL=0.9
         MAX_NUM_BATCHED_TOKENS=8192
         ;;
-    8|10)
+    8)
+        SYNTHETIC_ACCEPT_LEN=3.84
+        SPEC_NUM_TOKENS=7
+        GPU_MEM_UTIL=0.9
+        MAX_NUM_BATCHED_TOKENS=8192
+        ;;
+    10)
         SYNTHETIC_ACCEPT_LEN=3.36
         SPEC_NUM_TOKENS=4
         GPU_MEM_UTIL=0.9
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index 543c40458..812aefec2 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -653,7 +653,7 @@ dsr1-fp8-mi355x-sglang-disagg-mtp:
           dp-attn: false
 
 kimik3-fp4-mi355x-vllm-agentic-mtp:
-  image: vllm/vllm-openai-rocm:nightly-rocm100-af1c01499b289be555c475669ba50a88e96d846e
+  image: vllm/vllm-openai-rocm:nightly-rocm100-29468dde8b515031dc6d4d9d06bf0a2fa0442098
   model: moonshotai/Kimi-K3
   model-prefix: kimik3
   runner: cluster:mi355x-amds
@@ -662,11 +662,12 @@ kimik3-fp4-mi355x-vllm-agentic-mtp:
   multinode: false
   scenarios:
     agentic-coding:
-    - dram-utilization: 0.60
+    - dram-utilization: 0.50
       search-space:
-      - { tp: 8, ep: 1, dcp-size: 1, kv-offloading: none, conc-list: [1, 4] , spec-decoding: mtp}
-      - { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, conc-list: [8, 10, 12, 14], spec-decoding: mtp }
-      - { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, conc-list: [44, 48, 70], spec-decoding: mtp }
+      #- { tp: 8, ep: 1, dcp-size: 1, kv-offloading: none, conc-list: [1, 4] , spec-decoding: mtp}
+      #- { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.6.dev101+rocm7.2" }, conc-list: [4, 8, 10, 12, 14], spec-decoding: mtp }
+      #- { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.6.dev101+rocm7.2" }, conc-list: [44, 48, 70], spec-decoding: mtp }
+      - { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.6.dev101+rocm7.2" }, conc-list: [70, 80], spec-decoding: mtp }
 
 # Kimi-K3 MXFP4 agentic-coding benchmark on MI355X via ATOM with DSpark
 # speculative decoding. Acceptance is pinned to the committed golden curve in
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 1bc132cd3..4e7ccf26f 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -8950,3 +8950,13 @@
   description:
     - "Update SGLang image from v0.5.19-cu130 to v0.5.20-cu130 and pass --cuda-graph-max-bs-decode after the alias removal."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3334
+
+- config-keys:
+    - kimik3-fp4-mi355x-vllm-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Select the SiTUv2 a4w4 FlyDSL MoE path via the canonical VLLM_ROCM_USE_AITER_MOE_SITUV2=1 flag and drop the deprecated VLLM_ROCM_USE_AITER_MOE_SITUV2_A8W4 alias and the legacy AITER_SITUV2_A8W4 override. vLLM exports AITER_SITUV2_A4W4=1 from this flag at init and clears any AITER_SITUV2_A8W4 (AITER checks A8W4 first); the tuned a4w4 dispatch needs AITER >= v0.1.20 (ROCm/aiter#4463), otherwise FlyDSL falls back to heuristic configs. This selects the fp4-activation MoE kernels and does not change the target or DSpark draft model weight precision."
+    - "Refresh the vLLM ROCm image to vllm/vllm-openai-rocm:nightly-rocm100-29468dde8b515031dc6d4d9d06bf0a2fa0442098 and bump the LMCache host KV tier to 0.5.6.dev101+rocm7.2."
+    - "Trim the search space to a single lmcache DRAM-offload arm at TP8/DCP8, conc [70, 80], dram-utilization 0.50, spec-decoding mtp; the earlier GPU-resident and vllm-simple arms are commented out for this re-sweep."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3447