diff --git a/benchmarks/single_node/agentic/dsv4_fp4_b200_sglang_mtp.sh b/benchmarks/single_node/agentic/dsv4_fp4_b200_sglang_mtp.sh
index 884705c148..182ec81bf0 100755
--- a/benchmarks/single_node/agentic/dsv4_fp4_b200_sglang_mtp.sh
+++ b/benchmarks/single_node/agentic/dsv4_fp4_b200_sglang_mtp.sh
@@ -101,14 +101,19 @@ fi
 
 PARALLEL_ARGS=(--tp "$TP")
 METRICS_ARGS=(--enable-metrics --enable-cache-report)
+MODEL_ARGS=()
 CHUNKED_PREFILL_SIZE=8192
+SWA_FULL_TOKENS_RATIO=0.1
 if [ "$DP_ATTENTION" = "true" ]; then
     DEEPEP_CONFIG='{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+    MODEL_ARGS+=(--enable-deepseek-v4-fp4-indexer)
     export SGLANG_OPT_USE_DEEPGEMM_MEGA_MOE=1
+    export SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS=1
+    export SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND=1
     export SGLANG_OPT_FIX_HASH_MEGA_MOE=1
     export SGLANG_OPT_USE_FAST_MASK_EP=1
     export SGLANG_OPT_FIX_MEGA_MOE_MEMORY=1
-    export SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=4096
+    export SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8192
     export SGLANG_OPT_FIX_NEXTN_MEGA_MOE=1
     export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=0
     PARALLEL_ARGS+=(
@@ -123,7 +128,9 @@ if [ "$DP_ATTENTION" = "true" ]; then
         --moe-a2a-backend deepep
         --deepep-config "$DEEPEP_CONFIG"
     )
-    CHUNKED_PREFILL_SIZE=32768
+    # This is the global budget across all eight DP-attention ranks.
+    CHUNKED_PREFILL_SIZE=65536
+    SWA_FULL_TOKENS_RATIO=0.02
 else
     PARALLEL_ARGS+=(
         --moe-runner-backend flashinfer_mxfp4
@@ -131,7 +138,6 @@ else
     )
 fi
 
-MODEL_ARGS=()
 # The B200-specialized image deadlocks immediately after weight loading when
 # forced through the B300 compressed-attention/page-size overrides.
 # DeepGEMM's DSv4 indexer needs a multi-GiB temporary allocation at long
@@ -186,7 +192,7 @@ SGLANG_CMD=(
     --trust-remote-code
     "${PARALLEL_ARGS[@]}"
     --mem-fraction-static "$MEM_FRACTION_STATIC"
-    --swa-full-tokens-ratio 0.1
+    --swa-full-tokens-ratio "$SWA_FULL_TOKENS_RATIO"
     --max-running-requests "$MAX_RUNNING_REQUESTS"
     --cuda-graph-max-bs "$CUDA_GRAPH_MAX_BS"
     --chunked-prefill-size "$CHUNKED_PREFILL_SIZE"
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 7290e3c3db..a995310234 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -941,9 +941,9 @@ dsv4-fp4-b200-sglang-agentic-hicache-mtp:
     - dram-utilization: 0.80
       search-space:
       - { tp: 8, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 2, 3, 4, 5] }
-      - { tp: 8, kv-offloading: dram, kv-offload-backend: { name: hicache }, spec-decoding: mtp, conc-list: [8, 10, 16, 32, 40, 44] }
-      - { tp: 8, ep: 8, dp-attn: true, kv-offloading: none, spec-decoding: mtp, conc-list: [16, 24, 32, 38, 44, 48, 50, 52], router: { name: sglang-router, version: "0.3.2" } }
-      - { tp: 8, ep: 8, dp-attn: true, kv-offloading: dram, kv-offload-backend: { name: hicache }, spec-decoding: mtp, conc-list: [16, 32, 38, 44, 50, 56, 64, 66, 68], router: { name: sglang-router, version: "0.3.2" } }
+      - { tp: 8, kv-offloading: dram, kv-offload-backend: { name: hicache }, spec-decoding: mtp, conc-list: [8, 10, 16, 32] }
+      - { tp: 8, ep: 8, dp-attn: true, kv-offloading: none, spec-decoding: mtp, conc-list: [16], router: { name: sglang-router, version: "0.3.2" } }
+      - { tp: 8, ep: 8, dp-attn: true, kv-offloading: dram, kv-offload-backend: { name: hicache }, spec-decoding: mtp, conc-list: [16, 40, 48], router: { name: sglang-router, version: "0.3.2" } }
 
 dsv4-fp4-b200-vllm:
   image: vllm/vllm-openai:v0.25.0
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 85cb52f060..538a800d95 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6153,3 +6153,11 @@
     - "Add MiniMax-M3 NVFP4 B300 single-node TensorRT-LLM AgentX with EAGLE3-GQA speculative decoding (3 draft tokens)."
     - "Use the nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc23.post1 image."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2658
+
+- config-keys:
+    - dsv4-fp4-b200-sglang-agentic-hicache-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Update the B200 SGLang AgentX HiCache MTP DEP8 configuration."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2656