diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index f8cc486b2..fed0f2119 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2208,7 +2208,7 @@ qwen3.5-fp4-b200-sglang-mtp:
       - { tp: 2, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp }
 
 glm5-fp8-b200-sglang:
-  image: lmsysorg/sglang:v0.5.12-cu130
+  image: lmsysorg/sglang:nightly-dev-cu13-20260523-c112f762
   model: zai-org/GLM-5-FP8
   model-prefix: glm5
   runner: b200
@@ -2227,7 +2227,7 @@ glm5-fp8-b200-sglang:
       - { tp: 8, ep: 1, conc-start: 4, conc-end: 256 }
 
 glm5-fp8-b200-sglang-mtp:
-  image: lmsysorg/sglang:v0.5.12-cu130
+  image: lmsysorg/sglang:nightly-dev-cu13-20260523-c112f762
   model: zai-org/GLM-5-FP8
   model-prefix: glm5
   runner: b200
@@ -2307,7 +2307,7 @@ glm5-fp8-b300-sglang-mtp:
       - { tp: 8, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp }
 
 glm5-fp4-b200-sglang:
-  image: lmsysorg/sglang:v0.5.12-cu130
+  image: lmsysorg/sglang:nightly-dev-cu13-20260523-c112f762
   model: nvidia/GLM-5-NVFP4
   model-prefix: glm5
   runner: b200
@@ -2328,7 +2328,7 @@ glm5-fp4-b200-sglang:
       - { tp: 4, ep: 1, conc-start: 4, conc-end: 256 }
 
 glm5-fp4-b200-sglang-mtp:
-  image: lmsysorg/sglang:v0.5.12-cu130
+  image: lmsysorg/sglang:nightly-dev-cu13-20260523-c112f762
   model: nvidia/GLM-5-NVFP4
   model-prefix: glm5
   runner: b200
diff --git a/benchmarks/single_node/glm5_fp8_b200.sh b/benchmarks/single_node/glm5_fp8_b200.sh
index ccaa87b98..2cd84dddc 100755
--- a/benchmarks/single_node/glm5_fp8_b200.sh
+++ b/benchmarks/single_node/glm5_fp8_b200.sh
@@ -45,7 +45,6 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --tool-call-parser glm47 \
 --reasoning-parser glm45 \
 --kv-cache-dtype fp8_e4m3 --quantization fp8 \
---fp8-gemm-backend cutlass \
 --attention-backend nsa \
 --nsa-decode-backend trtllm --nsa-prefill-backend trtllm \
 --moe-runner-backend flashinfer_trtllm \
diff --git a/benchmarks/single_node/glm5_fp8_b200_mtp.sh b/benchmarks/single_node/glm5_fp8_b200_mtp.sh
index 5e4f98533..ecd5ca0af 100755
--- a/benchmarks/single_node/glm5_fp8_b200_mtp.sh
+++ b/benchmarks/single_node/glm5_fp8_b200_mtp.sh
@@ -46,7 +46,6 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --tool-call-parser glm47 \
 --reasoning-parser glm45 \
 --kv-cache-dtype fp8_e4m3 --quantization fp8 \
---fp8-gemm-backend cutlass \
 --attention-backend nsa \
 --nsa-decode-backend trtllm --nsa-prefill-backend trtllm \
 --moe-runner-backend flashinfer_trtllm \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index b7182a39c..941ee7d72 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3192,3 +3192,12 @@
     - "Add GLM-5-FP8 models.yaml flags, setup_deps.sh (aiter gluon + transformers glm_moe_dsa), GLM-5 env tuning in env.sh"
     - "Add multinode launch script glm5_fp8_mi355x_sglang-disagg.sh; server.sh sources setup_deps.sh"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1572
+
+- config-keys:
+    - glm5-fp4-b200-sglang
+    - glm5-fp4-b200-sglang-mtp
+    - glm5-fp8-b200-sglang
+    - glm5-fp8-b200-sglang-mtp
+  description:
+    - "Update SGLang image from v0.5.11-cu130 to nightly-dev-cu13-20260523-c112f762"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1567