diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml
new file mode 100644
index 000000000..b4a8864fa
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml
@@ -0,0 +1,235 @@
+base:
+  name: gb200-fp4-glm5-mtp
+  model:
+    path: glm-5-fp4
+    container: "lmsysorg/sglang:v0.5.13.post1-cu130"
+    precision: fp4
+  identity:
+    model:
+      repo: nvidia/GLM-5-NVFP4
+      revision: dc54ff55a7e9e71b85db953d8bc22eca894b44c6
+    frameworks:
+      dynamo: 1.2.1
+      sglang: 0.5.13.post1
+  resources:
+    gpu_type: gb200
+    gpus_per_node: 4
+  frontend:
+    type: dynamo
+  dynamo:
+    version: 1.2.1
+  backend:
+    type: sglang
+    prefill_environment:
+      TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: '1800'
+      PYTHONUNBUFFERED: '1'
+      DYN_SKIP_SGLANG_LOG_FORMATTING: '1'
+      SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: '100000'
+      SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: '100000'
+      SGLANG_DISAGGREGATION_WAITING_TIMEOUT: '100000'
+      MC_TE_METRIC: 'true'
+      MC_FORCE_MNNVL: '1'
+      NCCL_MNNVL_ENABLE: '1'
+      NCCL_CUMEM_ENABLE: '1'
+      SGLANG_MOONCAKE_CUSTOM_MEM_POOL: 'True'
+      SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: '0'
+      SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: '1'
+    decode_environment:
+      TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: '1800'
+      PYTHONUNBUFFERED: '1'
+      DYN_SKIP_SGLANG_LOG_FORMATTING: '1'
+      SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: '100000'
+      SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: '100000'
+      SGLANG_DISAGGREGATION_WAITING_TIMEOUT: '100000'
+      MC_TE_METRIC: 'true'
+      MC_FORCE_MNNVL: '1'
+      NCCL_MNNVL_ENABLE: '1'
+      NCCL_CUMEM_ENABLE: '1'
+      SGLANG_MOONCAKE_CUSTOM_MEM_POOL: 'True'
+      SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: '0'
+      SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: '1'
+      SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: '512'
+      SGLANG_MOE_NVFP4_DISPATCH: '1'
+    sglang_config:
+      prefill:
+        served-model-name: GLM-5-FP4
+        trust-remote-code: true
+        quantization: modelopt_fp4
+        kv-cache-dtype: fp8_e4m3
+        disaggregation-mode: prefill
+        disaggregation-transfer-backend: nixl
+        max-running-requests: 136
+        cuda-graph-max-bs: 136
+        mem-fraction-static: 0.812
+        context-length: 9280
+        chunked-prefill-size: 65536
+        max-prefill-tokens: 16384
+        tensor-parallel-size: 4
+        data-parallel-size: 4
+        expert-parallel-size: 4
+        enable-dp-attention: true
+        enable-dp-lm-head: true
+        load-balance-method: total_tokens
+        nsa-decode-backend: trtllm
+        nsa-prefill-backend: trtllm
+        moe-runner-backend: flashinfer_trtllm
+        fp4-gemm-backend: flashinfer_cutlass
+        enable-flashinfer-allreduce-fusion: true
+        disable-radix-cache: true
+        weight-loader-prefetch-checkpoints: true
+        model-loader-extra-config: '{"enable_multithread_load": true}'
+      decode:
+        served-model-name: GLM-5-FP4
+        trust-remote-code: true
+        quantization: modelopt_fp4
+        kv-cache-dtype: fp8_e4m3
+        disaggregation-mode: decode
+        disaggregation-transfer-backend: nixl
+        speculative-algorithm: EAGLE
+        speculative-num-steps: 2
+        speculative-eagle-topk: 1
+        speculative-num-draft-tokens: 3
+        tensor-parallel-size: 4
+        data-parallel-size: 1
+        expert-parallel-size: 1
+        enable-dp-attention: false
+        enable-dp-lm-head: false
+        load-balance-method: round_robin
+        max-running-requests: 22
+        cuda-graph-max-bs: 22
+        chunked-prefill-size: 64
+        context-length: 9280
+        nsa-prefill-backend: trtllm
+        nsa-decode-backend: trtllm
+        moe-runner-backend: flashinfer_trtllm
+        fp4-gemm-backend: flashinfer_cutlass
+        mem-fraction-static: 0.918
+        skip-tokenizer-init: true
+        stream-interval: 30
+        disable-radix-cache: true
+        enable-flashinfer-allreduce-fusion: true
+        weight-loader-prefetch-checkpoints: true
+        model-loader-extra-config: '{"enable_multithread_load": true}'
+  health_check:
+    max_attempts: 360
+    interval_seconds: 10
+  benchmark:
+    type: sa-bench
+    req_rate: inf
+# ################# 8k1k #################
+zip_override_mtp_8k1k_hightpt:
+  name: [8k1k-1p1d_dep16, 8k1k-2p1d_dep16, 8k1k-4p1d_dep16, 8k1k-8p1d_dep16]
+  backend:
+    decode_environment:
+      SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+    sglang_config:
+      decode:
+        cuda-graph-max-bs: [91, 196, 451, 1354]
+        data-parallel-size: 16
+        deepep-config: /configs/deepep_config.json
+        deepep-mode: low_latency
+        enable-dp-attention: true
+        enable-dp-lm-head: true
+        enable-flashinfer-allreduce-fusion: false
+        ep-dispatch-algorithm: static
+        ep-num-redundant-experts: 0
+        expert-parallel-size: 16
+        load-balance-method: null
+        max-running-requests: [91, 196, 451, 1354]
+        mem-fraction-static: 0.858
+        moe-a2a-backend: deepep
+        moe-dense-tp-size: 1
+        moe-runner-backend: flashinfer_cutedsl
+        speculative-moe-a2a-backend: deepep
+        speculative-moe-runner-backend: deep_gemm
+        tensor-parallel-size: 16
+  benchmark:
+    concurrencies: [[109], [398], [853], [2132]]
+    isl: 8192
+    osl: 1024
+  resources:
+    decode_nodes: 4
+    decode_workers: 1
+    prefill_nodes: [1, 2, 4, 8]
+    prefill_workers: [1, 2, 4, 8]
+zip_override_mtp_8k1k_lowlat:
+  name: [8k1k-1p4d_tp4, 8k1k-1p4d_tp4-conc16, 8k1k-1p8d_tp4, 8k1k-1p8d_tp4-conc4, 8k1k-1p16d_tp4, 8k1k-1p16d_tp4-conc1]
+  backend:
+    sglang_config:
+      decode:
+        cuda-graph-max-bs: [22, 15, 9, 4, 4, 1]
+        max-running-requests: [22, 15, 9, 4, 4, 1]
+  benchmark:
+    concurrencies: [[104], [82], [87], [47], [74], [26]]
+    isl: 8192
+    osl: 1024
+  resources:
+    decode_nodes: [4, 4, 8, 8, 16, 16]
+    decode_workers: [4, 4, 8, 8, 16, 16]
+    prefill_nodes: 1
+    prefill_workers: 1
+# ################# 1k1k #################
+zip_override_mtp_1k1k_hightpt:
+  name: [1k1k-1p1d_dep16, 1k1k-1p1d_dep16-conc1024, 1k1k-1p1d_dep16-conc256, 1k1k-1p1d_dep32]
+  backend:
+    decode_environment:
+      SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE: '1'
+    sglang_config:
+      decode:
+        context-length: 2112
+        cuda-graph-max-bs: [1627, 958, 239, 1122]
+        data-parallel-size: [16, 16, 16, 32]
+        deepep-config: /configs/deepep_config.json
+        deepep-mode: low_latency
+        enable-dp-attention: true
+        enable-dp-lm-head: true
+        enable-flashinfer-allreduce-fusion: false
+        ep-dispatch-algorithm: static
+        ep-num-redundant-experts: 0
+        expert-parallel-size: [16, 16, 16, 32]
+        max-running-requests: [1627, 958, 239, 1122]
+        mem-fraction-static: [0.858, 0.858, 0.858, 0.845]
+        moe-a2a-backend: deepep
+        moe-dense-tp-size: 1
+        moe-runner-backend: flashinfer_cutedsl
+        speculative-moe-a2a-backend: deepep
+        speculative-moe-runner-backend: deep_gemm
+        tensor-parallel-size: [16, 16, 16, 32]
+      prefill:
+        context-length: 2112
+        cuda-graph-max-bs: 512
+        disable-cuda-graph: true
+        max-running-requests: 512
+        mem-fraction-static: 0.83
+  benchmark:
+    concurrencies: [[1742], [1150], [302], [1263]]
+    isl: 1024
+    osl: 1024
+  resources:
+    decode_nodes: [4, 4, 4, 8]
+    decode_workers: 1
+    prefill_nodes: 1
+    prefill_workers: 1
+zip_override_mtp_1k1k_lowlat:
+  name: [1k1k-1p16d_tp4-conc1, 1k1k-1p16d_tp4-conc16, 1k1k-1p16d_tp4-conc4]
+  backend:
+    sglang_config:
+      decode:
+        context-length: 2112
+        cuda-graph-max-bs: [1, 16, 4]
+        max-running-requests: [1, 16, 4]
+      prefill:
+        context-length: 2112
+        cuda-graph-max-bs: 512
+        disable-cuda-graph: true
+        max-running-requests: 512
+        mem-fraction-static: 0.83
+  benchmark:
+    concurrencies: [[26], [343], [94]]
+    isl: 1024
+    osl: 1024
+  resources:
+    decode_nodes: 16
+    decode_workers: 16
+    prefill_nodes: 1
+    prefill_workers: 1
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 8376b5b93..c3c6e7be4 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -9137,6 +9137,290 @@ dsv4-fp4-gb200-dynamo-sglang-mtp:
           tp: 16
           ep: 16
           dp-attn: true
+
+glm5-fp4-gb200-dynamo-sglang-mtp:
+  image: lmsysorg/sglang:v0.5.13.post1-cu130
+  model: nvidia/GLM-5.1-NVFP4
+  model-prefix: glm5.1
+  runner: gb200
+  precision: fp4
+  framework: dynamo-sglang
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    # ---------- 8k1k high-throughput (wide-EP TP=16 decode, MTP) ----------
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # 1p1d dep16. 5 nodes (1P + 4D).
+      - spec-decoding: "mtp"
+        conc-list: [109]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_hightpt[0]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 2p1d dep16. 6 nodes (2P + 4D).
+      - spec-decoding: "mtp"
+        conc-list: [398]
+        prefill:
+          num-worker: 2
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_hightpt[1]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 4p1d dep16. 8 nodes (4P + 4D).
+      - spec-decoding: "mtp"
+        conc-list: [853]
+        prefill:
+          num-worker: 4
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_hightpt[2]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 8p1d dep16. 12 nodes (8P + 4D).
+      - spec-decoding: "mtp"
+        conc-list: [2132]
+        prefill:
+          num-worker: 8
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_hightpt[3]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+    # ---------- 8k1k low-latency (per-node TP=4 decode workers, MTP) ----------
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # 1p4d tp4. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [104]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[0]"
+        decode:
+          num-worker: 4
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p4d tp4, conc16. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [82]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[1]"
+        decode:
+          num-worker: 4
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p8d tp4. 9 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [87]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[2]"
+        decode:
+          num-worker: 8
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p8d tp4, conc4. 9 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [47]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[3]"
+        decode:
+          num-worker: 8
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p16d tp4. 17 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [74]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[4]"
+        decode:
+          num-worker: 16
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p16d tp4, conc1. 17 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [26]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_8k1k_lowlat[5]"
+        decode:
+          num-worker: 16
+          tp: 4
+          ep: 1
+          dp-attn: false
+    # ---------- 1k1k high-throughput (wide-EP decode, MTP) ----------
+    - isl: 1024
+      osl: 1024
+      search-space:
+      # 1p1d dep16. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [1742]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_hightpt[0]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 1p1d dep16, conc1024. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [1150]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_hightpt[1]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 1p1d dep16, conc256. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [302]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_hightpt[2]"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # 1p1d dep32. 9 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [1263]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_hightpt[3]"
+        decode:
+          num-worker: 1
+          tp: 32
+          ep: 32
+          dp-attn: true
+    # ---------- 1k1k low-latency (per-node TP=4 decode workers, MTP) ----------
+    - isl: 1024
+      osl: 1024
+      search-space:
+      # 1p16d tp4, conc1. 17 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [26]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_lowlat[0]"
+        decode:
+          num-worker: 16
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p16d tp4, conc16. 17 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [343]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_lowlat[1]"
+        decode:
+          num-worker: 16
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # 1p16d tp4, conc4. 17 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [94]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/glm5/gb200-fp4/glm5-mtp.yaml:zip_override_mtp_1k1k_lowlat[2]"
+        decode:
+          num-worker: 16
+          tp: 4
+          ep: 1
+          dp-attn: false
+
 dsv4-fp4-b300-dynamo-vllm:
   image: vllm/vllm-openai:v0.23.0
   model: deepseek-ai/DeepSeek-V4-Pro
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 910e730e8..70f45732e 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4620,3 +4620,10 @@
     - "Add 8k/1k MTP disagg high-throughput points: 1p1d and 4p1d (DEP4 prefill / DEP8 decode) at conc 512."
     - "Add an 8k/1k MTP disagg 4p1d (DEP4 prefill / DEP8 decode) high-throughput point at conc 2048 with a dedicated engine tune (max-running-requests 2048, decode scheduler-recv-interval 1, prefill/decode stream-interval 100/34, SGLANG_HACK_SEQ_BOOTSTRAP_ROOM)."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2113
+
+- config-keys:
+    - glm5-fp4-gb200-dynamo-sglang-mtp
+  description:
+    - "Add GLM-5.1 NVFP4 GB200 disaggregated dynamo-sglang MTP config covering 8k1k and 1k1k, high-throughput and low-latency topologies"
+    - "Image: lmsysorg/sglang:v0.5.13.post1-cu130"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2115
diff --git a/runners/launch_gb200-nv.sh b/runners/launch_gb200-nv.sh
index 17b377819..b60f4f353 100755
--- a/runners/launch_gb200-nv.sh
+++ b/runners/launch_gb200-nv.sh
@@ -29,6 +29,11 @@ if [[ $FRAMEWORK == "dynamo-sglang" ]]; then
     elif [[ $MODEL_PREFIX == "qwen3.5" && $PRECISION == "fp8" ]]; then
         export MODEL_PATH="/mnt/lustre01/models/Qwen3.5-397B-A17B-FP8"
         export SRT_SLURM_MODEL_PREFIX="qwen3.5-fp8"
+    elif [[ $MODEL_PREFIX == "glm5.1" && $PRECISION == "fp4" ]]; then
+        # SRT_SLURM_MODEL_PREFIX matches the model.path alias ("glm-5-fp4")
+        # in our GLM-5.1 sglang recipes.
+        export MODEL_PATH="/mnt/lustre01/models/GLM-5.1-NVFP4"
+        export SRT_SLURM_MODEL_PREFIX="glm-5-fp4"
     elif [[ $MODEL_PREFIX == "glm5.1" && $PRECISION == "fp8" ]]; then
         # SRT_SLURM_MODEL_PREFIX matches the model.path alias ("glm-5.1-fp8")
         # in our GLM-5.1 sglang recipes.
@@ -502,7 +507,10 @@ fi
 
 SRTCTL_APPLY_ARGS=(
     "${PREFLIGHT_ARGS[@]}"
-    -f "$CONFIG_PATH"
+    # Pass the full CONFIG_FILE (not the stripped CONFIG_PATH): srtctl needs the
+    # ":zip_override_...[i]" selector to pick the recipe block. For plain-file
+    # recipes CONFIG_FILE == CONFIG_PATH, so this is a no-op for them.
+    -f "$CONFIG_FILE"
     --tags "gb200,${MODEL_PREFIX},${PRECISION},${ISL}x${OSL},infmax-$(date +%Y%m%d)"
 )
 if [[ "$FRAMEWORK" == "dynamo-sglang" ]]; then