diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 3d6a17ff7..e24ec38c0 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1756,7 +1756,7 @@ dsv4-fp4-b200-sglang:
       - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 512 }
 
 dsv4-fp4-b200-vllm:
-  image: vllm/vllm-openai:v0.22.0
+  image: vllm/vllm-openai:nightly-3f0a91bb96f8d72e0498b95c166e817deae14d62
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b200-dsv4
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_vllm.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_vllm.sh
index 8021e54e7..2cafd4b32 100755
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_vllm.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_vllm.sh
@@ -43,8 +43,10 @@ fi
 
 GMU_ARGS=()
 MOE_ARGS=()
+EPLB_ARGS=()
 if [ "${DP_ATTENTION}" = "true" ]; then
     MOE_ARGS=(--moe-backend deep_gemm_mega_moe)
+    EPLB_ARGS=(--enable-eplb --eplb-config '{"communicator":"torch_nccl", "use_async": false}')
 fi
 
 if [ "${ISL}" -eq 8192 ] && [ "${CONC}" -le 128 ]; then
@@ -78,6 +80,7 @@ vllm serve "$MODEL" --host 0.0.0.0 --port "$PORT" \
     "${EP_ARGS[@]}" \
     "${GMU_ARGS[@]}" \
     "${MOE_ARGS[@]}" \
+    "${EPLB_ARGS[@]}" \
     --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}' \
     --attention_config.use_fp4_indexer_cache=True \
     --tokenizer-mode deepseek_v4 \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index d69f528a8..eb23a6cc8 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3445,6 +3445,12 @@
     - "Add 1k1k/8k1k minimax recipe set under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1641
 
+- config-keys:
+    - dsv4-fp4-b200-vllm
+  description:
+    - "Enable EPLB for DEP configs"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1655
+
 - config-keys:
     - minimaxm2.5-fp8-gb300-dynamo-vllm
   description: