diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 70a79a273..fb0274784 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -427,7 +427,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
           - "DECODE_MTP_SIZE=0"
 
 qwen3.5-fp4-mi355x-sglang:
-  image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604
+  image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
   model: amd/Qwen3.5-397B-A17B-MXFP4
   model-prefix: qwen3.5
   runner: mi355x
@@ -469,7 +469,7 @@ qwen3.5-fp4-mi355x-atom:
       - { tp: 4, conc-start: 4, conc-end: 16 }
 
 qwen3.5-fp4-mi355x-sglang-mtp:
-  image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604
+  image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
   model: amd/Qwen3.5-397B-A17B-MXFP4
   model-prefix: qwen3.5
   runner: mi355x
diff --git a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
index 7d87eea27..b036e060e 100644
--- a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
+++ b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
@@ -19,6 +19,7 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi
 
 export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
+export AITER_FLYDSL_FORCE=1
 
 SERVER_LOG=/workspace/server.log
 MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
diff --git a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
index 317147668..8081b824e 100755
--- a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
@@ -19,6 +19,7 @@ hf download "$MODEL"
 
 export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
+export AITER_FLYDSL_FORCE=1
 
 SERVER_LOG=/workspace/server.log
 MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index c0642188b..4ba690d2e 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3600,3 +3600,11 @@
     - "MI355x DSR1-FP4: Include TP4 configurations for 8k1k"
     - "Expand the TP sweep (included TP=4) for 8k/1k configuration for conc=4 to 64"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1692
+
+- config-keys:
+    - qwen3.5-fp4-mi355x-sglang
+    - qwen3.5-fp4-mi355x-sglang-mtp
+  description:
+    - "Bump image from lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604 to lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612"
+    - "Enable AITER_FLYDSL_FORCE=1 in both non-MTP and MTP benchmark scripts"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1716