diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index cfc8e87ab..43b8be880 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2454,7 +2454,7 @@ qwen3.5-fp8-b300-sglang:
       - { tp: 4, ep: 1, conc-start: 4, conc-end: 256 }
 
 qwen3.5-fp4-b300-sglang:
-  image: lmsysorg/sglang:v0.5.11-cu130
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: nvidia/Qwen3.5-397B-A17B-NVFP4
   model-prefix: qwen3.5
   runner: b300
@@ -2475,7 +2475,7 @@ qwen3.5-fp4-b300-sglang:
       - { tp: 2, ep: 2, conc-start: 4, conc-end: 128 }
 
 qwen3.5-fp4-b300-sglang-mtp:
-  image: lmsysorg/sglang:v0.5.11-cu130
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: nvidia/Qwen3.5-397B-A17B-NVFP4
   model-prefix: qwen3.5
   runner: b300
diff --git a/benchmarks/single_node/qwen3.5_fp4_b300.sh b/benchmarks/single_node/qwen3.5_fp4_b300.sh
index e3ae6a6e4..18b6cda09 100755
--- a/benchmarks/single_node/qwen3.5_fp4_b300.sh
+++ b/benchmarks/single_node/qwen3.5_fp4_b300.sh
@@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
 --mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
 --context-length $CONTEXT_LENGTH --disable-radix-cache \
---attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
 $EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
 --tokenizer-worker-num 6 --stream-interval 30 > $SERVER_LOG 2>&1 &
 
diff --git a/benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh b/benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh
index 033c0408a..9cb5d5464 100755
--- a/benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh
+++ b/benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh
@@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
 --mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
 --context-length $CONTEXT_LENGTH --disable-radix-cache \
---attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
 $EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
 --tokenizer-worker-num 6 --stream-interval 30 \
 --speculative-algorithm EAGLE \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 45d8ba110..c62d94781 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3036,3 +3036,10 @@
     - "TP=4 shows +3.2% to +16.3% throughput improvement across 1k1k and 8k1k workloads (concurrency 4-256)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1411
   
+
+- config-keys:
+    - qwen3.5-fp4-b300-sglang
+    - qwen3.5-fp4-b300-sglang-mtp
+  description:
+    - "Update SGLang image from v0.5.11-cu130 (5d old) to v0.5.12-cu130"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1475