diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang.sh
index 2ced868365..79c5832db9 100755
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang.sh
@@ -26,27 +26,9 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi
 
 export SGLANG_DEFAULT_THINKING=1
 export SGLANG_DSV4_REASONING_EFFORT=max
-export SGLANG_OPT_DEEPGEMM_HC_PRENORM=false
-export SGLANG_USE_AITER=1
 export SGLANG_USE_ROCM700A=0
-export SGLANG_DP_USE_GATHERV=1
-export SGLANG_OPT_USE_FUSED_COMPRESS=true
 export SGLANG_HACK_FLASHMLA_BACKEND=unified_kv_triton
-export SGLANG_OPT_FP8_WO_A_GEMM=false
-export SGLANG_OPT_USE_JIT_INDEXER_METADATA=false
-export SGLANG_OPT_USE_TOPK_V2=false
-export SGLANG_OPT_USE_AITER_INDEXER=true
-export SGLANG_OPT_USE_TILELANG_INDEXER=false
-export SGLANG_OPT_USE_TILELANG_MHC_PRE=false
-export SGLANG_OPT_USE_TILELANG_MHC_POST=false
-export SGLANG_FP8_PAGED_MQA_LOGITS_TORCH=1
-export SGLANG_OPT_USE_FUSED_COMPRESS_TRITON=true
 export AITER_BF16_FP8_MOE_BOUND=0
-export SGLANG_EAGER_INPUT_NO_COPY=true
-
-# multi-stream
-export SGLANG_OPT_USE_MULTI_STREAM_OVERLAP=false
-export SGLANG_ROCM_USE_MULTI_STREAM=false
 
 SERVER_LOG=/workspace/server.log
 
@@ -63,12 +45,18 @@ PARALLEL_ARGS=(
 )
 CHUNKED_PREFILL_SIZE=$ISL
 if [ "${DP_ATTENTION}" = "true" ]; then
+    export SGLANG_SHARED_EXPERT_TP1=1
+    export SGLANG_DP_SHARED_EXPERT_LOCAL=1
+    export SGLANG_DP_USE_GATHERV=1
+    export SGLANG_DP_USE_REDUCE_SCATTER=1
+    export GPU_MAX_HW_QUEUES=5
+
     CHUNKED_PREFILL_SIZE=$((ISL * TP))
     PARALLEL_ARGS+=(
         --dp "$TP"
         --enable-dp-attention
         --enable-prefill-delayer
-	--prefill-delayer-max-delay-ms 5000
+        --enable-two-batch-overlap
     )
 fi
 if [ "${EP_SIZE:-1}" -gt 1 ]; then
@@ -83,10 +71,12 @@ sglang serve \
     --trust-remote-code \
     --disable-radix-cache \
     --attention-backend dsv4 \
+    --cuda-graph-max-bs ${CONC} \
     --max-running-requests ${CONC} \
     --mem-fraction-static 0.90 \
     --swa-full-tokens-ratio 0.15 \
     --page-size 256 \
+    --kv-cache-dtype fp8_e4m3 \
     --context-length $MAX_MODEL_LEN \
     --chunked-prefill-size $CHUNKED_PREFILL_SIZE \
     --disable-shared-experts-fusion \
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index f9a2a99e07..a2cb69db9e 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1736,7 +1736,7 @@ dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp:
           - "DECODE_MTP_SIZE=1"
 
 dsv4-fp4-mi355x-sglang:
-  image: lmsysorg/sglang-rocm:v0.5.13.post1-rocm720-mi35x-20260618
+  image: lmsysorg/sglang-rocm:v0.5.14-rocm720-mi35x-20260706
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: mi355x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 806996178a..f5e0ff4284 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4684,3 +4684,11 @@
     - "Image: lmsysorg/sglang:v0.5.11-cu130"
     - "11 topologies across 1k/1k and 8k/1k (prefill TP4 + decode wide-EP: 8k/1k DEP16/24/32/40, 1k/1k DEP48/56; per-node TP4 low-latency); MTP flags: speculative-algorithm EAGLE, num-steps 2, eagle-topk 1, num-draft-tokens 3"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1907
+  
+- config-keys:
+    - dsv4-fp4-mi355x-sglang
+  description:
+    - "Bump image to lmsysorg/sglang-rocm:v0.5.14-rocm720-mi35x-20260706"
+    - "Clean the export envs"
+    - "Enable two batch overlap"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2093