diff --git a/benchmarks/single_node/dsv4_fp4_mi355x_sglang.sh b/benchmarks/single_node/dsv4_fp4_mi355x_sglang.sh
index 642c93918..dae0fc043 100755
--- a/benchmarks/single_node/dsv4_fp4_mi355x_sglang.sh
+++ b/benchmarks/single_node/dsv4_fp4_mi355x_sglang.sh
@@ -53,7 +53,7 @@ PYEOF
 #                                    the swiglu_limit clamp in the triton
 #                                    MoE fallback path.
 export SGLANG_REASONING_EFFORT=max
-export SGLANG_OPT_USE_FUSED_COMPRESS=false
+export SGLANG_OPT_USE_FUSED_COMPRESS=true
 export SGLANG_OPT_USE_OLD_COMPRESSOR=true
 export SGLANG_OPT_USE_TILELANG_SWA_PREPARE=false
 export SGLANG_OPT_USE_JIT_KERNEL_FUSED_TOPK=false
@@ -64,7 +64,7 @@ export SGLANG_OPT_USE_TILELANG_MHC_POST=false
 export SGLANG_ENABLE_THINKING=1
 export SGLANG_USE_AITER=1
 export SGLANG_USE_ROCM700A=1
-export SGLANG_TOPK_TRANSFORM_512_TORCH=1
+export SGLANG_TOPK_TRANSFORM_512_TORCH=0
 export SGLANG_FP8_PAGED_MQA_LOGITS_TORCH=1
 export SGLANG_DSV4_FP4_EXPERTS=True
 export SGLANG_OPT_DPSK_V4_RADIX=0
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 524c91e67..6f2a60d11 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -2171,6 +2171,13 @@
     - "ep=1 entries (dp-attn true and false) are unaffected by the EP=8 regression"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1266
 
+- config-keys:
+    - dsv4-fp4-mi355x-sglang
+  description:
+    - "Flip SGLANG_TOPK_TRANSFORM_512_TORCH from 1 to 0. The indexer's top-k step now runs the tilelang kernel instead of the torch path."
+    - "Flip SGLANG_OPT_USE_FUSED_COMPRESS from false to true. The DeepseekV4 compressor now goes through the fused triton path instead of the torch path."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1275
+
 - config-keys:
     - dsv4-fp4-gb200-dynamo-vllm-mtp2
   description: