diff --git a/benchmarks/single_node/agentic/dsv41flash_fp4_vllm_mtp.sh b/benchmarks/single_node/agentic/dsv41flash_fp4_vllm_mtp.sh
index 0a0a32629..2a0e8c584 100644
--- a/benchmarks/single_node/agentic/dsv41flash_fp4_vllm_mtp.sh
+++ b/benchmarks/single_node/agentic/dsv41flash_fp4_vllm_mtp.sh
@@ -77,6 +77,15 @@ if (( TP == 2 || (TP < 8 && GPU_MEM_MIB < 150000) )); then
     LOW_TP_ARGS=(--max-num-batched-tokens 4096 --max-num-seqs "$MAX_NUM_SEQS")
 fi
 
+# The SKU launcher opts into the Blackwell sparse indexer settings only
+# with an image that contains these backends. This script also serves H200.
+# TP2 and TP4 use FlashInfer sparse attention; fp8 resolves the backend KV layout.
+ATTENTION_ARGS=()
+if [[ "${DSV41_BLACKWELL_ATTENTION:-}" == true ]]; then
+    ATTENTION_CONFIG='{"backend":"FLASHINFER_MLA_SPARSE_DSV41","indexer_kv_dtype":"mxfp4","indexer_sparse_logits":true}'
+    ATTENTION_ARGS=(--attention-config "$ATTENTION_CONFIG" --kv-cache-dtype fp8)
+fi
+
 # Pyxis shares the host network; port 8888 can already belong to a host service.
 select_available_server_port
 export AIPERF_SERVER_URL="http://localhost:${PORT}"
@@ -99,6 +108,7 @@ VLLM_CMD=(
     --tool-call-parser deepseek_v41 --enable-auto-tool-choice
     --reasoning-parser deepseek_v41
     --engram-config '{"cpu_offload":true}'
+    "${ATTENTION_ARGS[@]}"
     --speculative-config "$SPEC_CONFIG"
     --max-model-len 1048576
     --max-cudagraph-capture-size "$CAPTURE_SIZE"
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 7ee2ca0be..e6ffcf981 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -8433,7 +8433,7 @@ dsv41flash-fp4-b300-vllm-agentic-dspark:
       - { tp: 2, kv-offloading: none, spec-decoding: mtp, conc-list: [2, 4, 8, 16, 32, 64, 128] }
 
 dsv41flash-fp4-b200-vllm-agentic-dspark:
-  image: vllm/vllm-openai:nightly-cd10ed6f9f6b37a8ace9cf380007e66fe12ec0c3
+  image: vllm/vllm-openai:nightly-0961bbae2894d574be790d219651824eb199318e
   model: deepseek-ai/DeepSeek-V4.1-Flash
   model-prefix: dsv41flash
   runner: cluster:b200-nscale
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 89f152cac..74111b2f6 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -8887,3 +8887,11 @@
     - "Add DeepSeek-V4-Pro-0813 golden AL for draft lengths 4, 5, 7 and 8 (3.36 / 3.61 / 3.73 / 3.47)."
     - "Agentic PD router: pin --decode-policy round_robin so decode no longer inherits the prefill --policy (consistent_hashing)."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3256
+
+- config-keys:
+    - dsv41flash-fp4-b200-vllm-agentic-dspark
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Pin B200 DeepSeek-V4.1-Flash vLLM to the 2026-09-22 nightly 0961bbae and opt in from its launcher to Blackwell sparse indexer logits, MXFP4 indexer KV, and fp8 KV cache; use FlashInfer sparse attention at TP2 and MegaAttention at TP4."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3393
diff --git a/runners/launch_b200-nscale-slurm.sh b/runners/launch_b200-nscale-slurm.sh
index f010f7676..61342b3ef 100755
--- a/runners/launch_b200-nscale-slurm.sh
+++ b/runners/launch_b200-nscale-slurm.sh
@@ -804,6 +804,10 @@ run_agentic() {
     if [[ "$MODEL_PREFIX" == "dsv41flash" ]]; then
         # Cover DSpark5 verification for concurrent AgentX subagents at c1/c2/c4.
         export DSV41_MIN_CUDAGRAPH_CAPTURE_SIZE=64
+        export VLLM_ENGINE_READY_TIMEOUT_S=7200
+        if [[ "$FRAMEWORK" == "vllm" ]]; then
+            export DSV41_BLACKWELL_ATTENTION=true
+        fi
         CONTAINER_MOUNT_DIR=/ix
         export INFMAX_CONTAINER_WORKSPACE=/ix
         export RESULT_DIR=/ix/results