diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 38d1101f3..4ce7b823e 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2604,6 +2604,30 @@ dsv4-fp8-h200-vllm:
       search-space:
       - { tp: 8, ep: 8, dp-attn: true, conc-start: 4, conc-end: 64 }
 
+# DeepSeek-V4-Pro H200 single-node with SGLang (Marlin FP8, TP-only).
+# Pinned to the h200-dgxc-slurm runner pool because the deepseek-v4-hopper
+# image needs the /ix mount layout that only launch_h200-dgxc-slurm.sh sets up.
+dsv4-fp8-h200-sglang:
+  image: lmsysorg/sglang:deepseek-v4-hopper@sha256:7f19c6dc092e47a10fac2e41f47eab78970280d06648b8e50d312a82f0ae722f
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: h200-dgxc
+  precision: fp8
+  framework: sglang
+  multinode: false
+  scenarios:
+    fixed-seq-len:
+    - isl: 1024
+      osl: 1024
+      search-space:
+      - { tp: 8, ep: 1, conc-start: 1, conc-end: 1 }
+      - { tp: 8, ep: 1, conc-start: 4, conc-end: 64 }
+    - isl: 8192
+      osl: 1024
+      search-space:
+      - { tp: 8, ep: 1, conc-start: 1, conc-end: 1 }
+      - { tp: 8, ep: 1, conc-start: 4, conc-end: 64 }
+
   # DeepSeek-V4-Pro B300 single-node aggregate recipe from the submitted B300
   # pareto sweep. The single-node schema has no explicit data-parallel-size
   # field, so dp-attn=true is used as the existing vLLM script switch for DP4
diff --git a/.github/configs/runners.yaml b/.github/configs/runners.yaml
index f574c629c..48a7173d4 100644
--- a/.github/configs/runners.yaml
+++ b/.github/configs/runners.yaml
@@ -49,6 +49,21 @@ h200-multinode:
 - 'h200-dgxc-slurm_11'
 - 'h200-dgxc-slurm_12'
 - 'h200-dgxc-slurm_13'
+h200-dgxc:
+- 'h200-dgxc-slurm_0'
+- 'h200-dgxc-slurm_1'
+- 'h200-dgxc-slurm_2'
+- 'h200-dgxc-slurm_3'
+- 'h200-dgxc-slurm_4'
+- 'h200-dgxc-slurm_5'
+- 'h200-dgxc-slurm_6'
+- 'h200-dgxc-slurm_7'
+- 'h200-dgxc-slurm_8'
+- 'h200-dgxc-slurm_9'
+- 'h200-dgxc-slurm_10'
+- 'h200-dgxc-slurm_11'
+- 'h200-dgxc-slurm_12'
+- 'h200-dgxc-slurm_13'
 b200:
 - 'b200-cw_00'
 - 'b200-cw_01'
diff --git a/benchmarks/single_node/dsv4_fp8_h200_sglang.sh b/benchmarks/single_node/dsv4_fp8_h200_sglang.sh
new file mode 100644
index 000000000..f2fc8541e
--- /dev/null
+++ b/benchmarks/single_node/dsv4_fp8_h200_sglang.sh
@@ -0,0 +1,74 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+nvidia-smi
+
+SERVER_LOG="$PWD/server.log"
+PORT=${PORT:-8888}
+
+echo "TP: $TP, CONC: $CONC, ISL: $ISL, OSL: $OSL"
+
+EVAL_CONTEXT_ARGS=""
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+    EVAL_CONTEXT_ARGS="--context-length $EVAL_MAX_MODEL_LEN"
+fi
+
+start_gpu_monitor --output "$PWD/gpu_metrics.csv"
+
+set -x
+PYTHONNOUSERSITE=1 sglang serve \
+    --model-path $MODEL \
+    --host 0.0.0.0 \
+    --port $PORT \
+    --trust-remote-code \
+    --tp $TP \
+    --moe-runner-backend marlin \
+    --chunked-prefill-size 4096 \
+    --disable-flashinfer-autotune \
+    --disable-radix-cache \
+    --mem-fraction-static 0.88 \
+    --max-running-requests "$(( CONC * 3 / 2 > 8 ? CONC * 3 / 2 : 8 ))" \
+    $EVAL_CONTEXT_ARGS >> $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts $((CONC * 10)) \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir "$PWD/"
+
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+stop_gpu_monitor
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 089ce36f2..6a4f08be5 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -2103,3 +2103,13 @@
     - "Sweep DP attention on/off and EP=8 via DP_ATTENTION and EP_SIZE matrix env vars"
     - "Ship a DeepSeek-V4 thinking-mode chat template so eval /v1/chat/completions works (the canonical checkpoint ships no chat_template)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1244
+
+- config-keys:
+    - dsv4-fp8-h200-sglang
+  description:
+    - "Add DeepSeek-V4-Pro FP8 H200 single-node SGLang recipe (Marlin MoE backend, TP=8, EP=1)"
+    - "Image: lmsysorg/sglang:deepseek-v4-hopper pinned by digest"
+    - "Server flags: --moe-runner-backend marlin, --chunked-prefill-size 4096, --disable-flashinfer-autotune, --disable-radix-cache, --mem-fraction-static 0.88"
+    - "Search space: TP=8 EP=1, conc 1 and 4-64 for both 1k1k and 8k1k"
+    - "Pinned to the h200-dgxc runner pool (new runners.yaml group); launch_h200-dgxc-slurm.sh extended to support framework-tagged script names and mount /ix instead of /workspace for the deepseek-v4-hopper image"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1264
diff --git a/runners/launch_h200-dgxc-slurm.sh b/runners/launch_h200-dgxc-slurm.sh
index 199f5e4ae..7dd04a6d7 100755
--- a/runners/launch_h200-dgxc-slurm.sh
+++ b/runners/launch_h200-dgxc-slurm.sh
@@ -292,13 +292,27 @@ else
         fi
     "
 
+    SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
+    BENCH_BASE="benchmarks/single_node/${SCENARIO_SUBDIR}${EXP_NAME%%_*}_${PRECISION}_h200"
+    BENCH_SCRIPT="${BENCH_BASE}_${FRAMEWORK}${SPEC_SUFFIX}.sh"
+    if [[ ! -f "$BENCH_SCRIPT" ]]; then
+        LEGACY_FW_SUFFIX=$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt' || printf '')
+        BENCH_SCRIPT="${BENCH_BASE}${LEGACY_FW_SUFFIX}${SPEC_SUFFIX}.sh"
+    fi
+
+    if [[ "$IMAGE" == *deepseek-v4-hopper* ]]; then
+        CONTAINER_MOUNT_DIR=/ix
+    else
+        CONTAINER_MOUNT_DIR=/workspace
+    fi
+
     srun --jobid=$JOB_ID \
         --container-image=$SQUASH_FILE \
-        --container-mounts=$GITHUB_WORKSPACE:/workspace/,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
+        --container-mounts=$GITHUB_WORKSPACE:$CONTAINER_MOUNT_DIR/,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
         --no-container-mount-home \
-        --container-workdir=/workspace/ \
+        --container-workdir=$CONTAINER_MOUNT_DIR/ \
         --no-container-entrypoint --export=ALL,PORT=8888 \
-        bash benchmarks/single_node/${SCENARIO_SUBDIR}${EXP_NAME%%_*}_${PRECISION}_h200$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt')$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp').sh
+        bash $BENCH_SCRIPT
 
     scancel $JOB_ID