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 87809f54b6..f31cb41b14 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
@@ -21,6 +21,7 @@ export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
 export AITER_FLYDSL_FORCE=1
 export SGLANG_MAMBA_SSM_DTYPE=bfloat16
+export SGLANG_USE_AITER_FP8_PER_TOKEN=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 16e86e5443..3c3ef258a4 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
@@ -21,6 +21,7 @@ export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
 export AITER_FLYDSL_FORCE=1
 export SGLANG_MAMBA_SSM_DTYPE=bfloat16
+export SGLANG_USE_AITER_FP8_PER_TOKEN=1
 
 SERVER_LOG=/workspace/server.log
 MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index 2195bad7e2..cd19b52a38 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -314,7 +314,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
 
 qwen3.5-fp4-mi355x-sglang:
   image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730
-  model: amd/Qwen3.5-397B-A17B-MXFP4
+  model: amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2
   model-prefix: qwen3.5
   runner: mi355x
   precision: fp4
@@ -346,7 +346,7 @@ qwen3.5-fp4-mi355x-atom:
 
 qwen3.5-fp4-mi355x-sglang-mtp:
   image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730
-  model: amd/Qwen3.5-397B-A17B-MXFP4
+  model: amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2
   model-prefix: qwen3.5
   runner: mi355x
   precision: fp4
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index d90a270383..1497ac0bb9 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6409,3 +6409,13 @@
     - "Require dcgm-power telemetry on the GLM-5.2 H200 disaggregated AgentX recipe."
     - "Enable dcgm-power telemetry on the DSV4 H200 aggregated AgentX recipe."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2684
+
+- config-keys:
+    - qwen3.5-fp4-mi355x-sglang
+    - qwen3.5-fp4-mi355x-sglang-mtp
+  scenario-type:
+    - fixed-seq-len
+  description:
+    - "Switch the served checkpoint from amd/Qwen3.5-397B-A17B-MXFP4 to amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2 on both arms."
+    - "Export SGLANG_USE_AITER_FP8_PER_TOKEN=1 on both arms, as the checkpoint's published SGLang recipe requires."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2695