diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg-mtp-variants.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg-mtp-variants.yaml
index a9c3b602b3..858502c910 100644
--- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg-mtp-variants.yaml
+++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg-mtp-variants.yaml
@@ -61,7 +61,7 @@ base:
         SGLANG_HICACHE_DEBUG_LOG: '1'
         SGLANG_HICACHE_DEBUG_SAMPLE_RATE: '16384'
         SGLANG_MOE_NVFP4_DISPATCH: '1'
-        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '0'
         SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: '8'
         PIP_BREAK_SYSTEM_PACKAGES: '1'
       args:
diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg.yaml
index 01e2442933..eae2807daf 100644
--- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg.yaml
+++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/agg.yaml
@@ -51,7 +51,7 @@ roles:
       SGLANG_HICACHE_DEBUG_LOG: '1'
       SGLANG_HICACHE_DEBUG_SAMPLE_RATE: '16384'
       SGLANG_MOE_NVFP4_DISPATCH: '1'
-      SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+      SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '0'
       SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: '8'
       PIP_BREAK_SYSTEM_PACKAGES: '1'
       SGLANG_DG_CACHE_DIR: /deepgemm_cache
diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-dep8-mtp-variants.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-dep8-mtp-variants.yaml
index 6411d5880e..c439698894 100644
--- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-dep8-mtp-variants.yaml
+++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-dep8-mtp-variants.yaml
@@ -7,17 +7,17 @@ schema: 2
 base:
   model:
     path: glm-5.2-fp4
-    container: dynamo-sglang
+    container: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
     precision: fp4
   identity:
     model:
       repo: nvidia/GLM-5.2-NVFP4
       revision: aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa
     container:
-      image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
+      image: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
     frameworks:
       dynamo: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
-      sglang: nightly-dev-cu13-20260805-211ee642
+      sglang: 0.5.18
   resources:
     gpu_type: gb200
     gpus_per_node: 4
@@ -124,7 +124,7 @@ base:
         SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: '1'
         SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: '512'
         SGLANG_MOE_NVFP4_DISPATCH: '1'
-        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '0'
         SGLANG_ENABLE_THINKING: '1'
         SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: '8'
         SGLANG_REASONING_EFFORT: max
diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-mtp-variants.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-mtp-variants.yaml
index ecf94a8d60..5a479c2665 100644
--- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-mtp-variants.yaml
+++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/glm5.2/sglang/gb200-fp4/agentx/disagg-mtp-variants.yaml
@@ -3,17 +3,17 @@ base:
   name: gb200-fp4-glm5.2-agentx
   model:
     path: glm-5.2-fp4
-    container: dynamo-sglang
+    container: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
     precision: fp4
   identity:
     model:
       repo: nvidia/GLM-5.2-NVFP4
       revision: aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa
     container:
-      image: lmsysorg/sglang:v0.5.17-cu130
+      image: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
     frameworks:
       dynamo: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
-      sglang: 0.5.17
+      sglang: 0.5.18
   resources:
     gpu_type: gb200
     gpus_per_node: 4
@@ -130,7 +130,7 @@ base:
         SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: '1'
         SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: '512'
         SGLANG_MOE_NVFP4_DISPATCH: '1'
-        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+        SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '0'
         SGLANG_ENABLE_THINKING: '1'
         SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: '8'
         SGLANG_REASONING_EFFORT: max
diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml
index 38cff92195..325446524e 100644
--- a/inferencex-e2e/configs/nvidia-master.yaml
+++ b/inferencex-e2e/configs/nvidia-master.yaml
@@ -7591,7 +7591,7 @@ glm5.2-fp4-gb200-dynamo-sglang-agentic-agg:
           # Shared deployment GPU power telemetry.
           - "CONFIG_FILE=recipes/glm5.2/sglang/gb200-fp4/agentx/agg.yaml"
 glm5.2-fp4-gb200-dynamo-sglang-agentic-disagg:
-  image: lmsysorg/sglang:v0.5.17-cu130
+  image: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
   model: nvidia/GLM-5.2-NVFP4
   model-prefix: glm5.2
   runner: cluster:gb200-nv
@@ -7625,7 +7625,7 @@ glm5.2-fp4-gb200-dynamo-sglang-agentic-disagg:
 # GLM-5.2 NVFP4 GB200 AgentX disaggregated variants use the committed
 # thinking-on golden acceptance length for two speculative tokens.
 glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp:
-  image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
+  image: lmsysorg/sglang:v0.5.18-cu130@sha256:db37df8aded8fa169f7264404f3c893672f8046609a4a43d15bedcb4f63d692a
   model: nvidia/GLM-5.2-NVFP4
   model-prefix: glm5.2
   runner: cluster:gb200-nv
diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml
index 31b46a207f..77f18a2b7f 100644
--- a/inferencex-e2e/perf-changelog.yaml
+++ b/inferencex-e2e/perf-changelog.yaml
@@ -9370,3 +9370,15 @@
     - "Run decoder SWA bounded replay with prefill graphs disabled on every point."
     - "Throughput keeps the committed thinking-on golden AL 3.51 selected by the srt connector; evals use real verification."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3696
+
+- config-keys:
+    - glm5.2-fp4-gb200-dynamo-sglang-agentic-agg
+    - glm5.2-fp4-gb200-dynamo-sglang-agentic-disagg
+    - glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp
+    - glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp-agg
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Keep the GLM-5.2 NextN/MTP draft at shipped precision on GB200."
+    - "Use the digest-pinned upstream SGLang v0.5.18 CUDA 13 image with NIXL 1.4.0 for the two disaggregated recipes."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3401