diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index ec9cbc11e..a758c7df0 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2363,6 +2363,24 @@ dsr1-fp8-h200-sglang:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+dsv4-fp8-h200-sglang:
+  image: lmsysorg/sglang:deepseek-v4-hopper
+  model: sgl-project/DeepSeek-V4-Flash-FP8
+  model-prefix: dsv4
+  runner: h200
+  precision: fp8
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 32 }
+
 qwen3.5-fp8-h200-sglang:
   image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: Qwen/Qwen3.5-397B-A17B-FP8
diff --git a/benchmarks/single_node/dsv4_fp8_h200.sh b/benchmarks/single_node/dsv4_fp8_h200.sh
new file mode 100755
index 000000000..45220dc3d
--- /dev/null
+++ b/benchmarks/single_node/dsv4_fp8_h200.sh
@@ -0,0 +1,76 @@
+#!/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
+
+export SGLANG_JIT_DEEPGEMM_PRECOMPILE=0
+export SGLANG_DSV4_FP4_EXPERTS=0
+
+# TODO(Cam): the lmsysorg/sglang:deepseek-v4-hopper image installs sglang editable
+# at /workspace/sglang/python (prior sglang tags used /sgl-workspace/sglang), so
+# the default $GITHUB_WORKSPACE:/workspace/ bind-mount masks the install. The
+# runner mounts at /ix for this image; paths here are $PWD-relative to be agnostic.
+# Drop once lmsys moves sglang back out of /workspace.
+
+SERVER_LOG="$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 python3 -m sglang.launch_server --model-path $MODEL --host 0.0.0.0 --port $PORT --trust-remote-code \
+--tp $TP \
+--moe-runner-backend flashinfer_mxfp4 \
+--chunked-prefill-size 4096 \
+--disable-flashinfer-autotune \
+--disable-radix-cache $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 ddc6409c2..6ff2c8c35 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1,3 +1,13 @@
+- config-keys:
+    - dsv4-fp8-h200-sglang
+  description:
+    - "Add DeepSeek-V4-Flash-FP8 single-node H200 SGLang benchmark (TP4)"
+    - "Container: lmsysorg/sglang:deepseek-v4-hopper"
+    - "Model: sgl-project/DeepSeek-V4-Flash-FP8"
+    - "Recipe from https://docs.sglang.io/cookbook/autoregressive/DeepSeek/DeepSeek-V4"
+    - "Prefix caching and speculative decoding disabled for baseline numbers"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/TBD
+
 - config-keys:
     - dsr1-fp8-h100-dynamo-trt
     - dsr1-fp8-h100-dynamo-sglang
diff --git a/runners/launch_h200-cw.sh b/runners/launch_h200-cw.sh
index 657f84792..5e971e659 100644
--- a/runners/launch_h200-cw.sh
+++ b/runners/launch_h200-cw.sh
@@ -11,6 +11,17 @@ PARTITION="h200"
 SQUASH_FILE="/mnt/vast/gharunner/squash/$(echo "$IMAGE" | sed 's/[\/:@#]/_/g').sqsh"
 LOCK_FILE="${SQUASH_FILE}.lock"
 
+# TODO(Cam): lmsysorg/sglang:deepseek-v4-hopper installs sglang editable at
+# /workspace/sglang/python (prior sglang tags used /sgl-workspace/sglang), so
+# the default $GITHUB_WORKSPACE:/workspace/ bind-mount masks the install and
+# breaks `import sglang`. Mount this one image at /ix instead; drop the
+# conditional once the image stops installing editable under /workspace.
+if [[ "$IMAGE" == *deepseek-v4-hopper* ]]; then
+    CONTAINER_MOUNT_DIR=/ix
+else
+    CONTAINER_MOUNT_DIR=/workspace
+fi
+
 set -x
 
 JOB_ID=$(salloc --partition=$PARTITION --gres=gpu:$TP --exclusive --time=180 --no-shell --job-name="$RUNNER_NAME" 2>&1 | tee /dev/stderr | grep -oP 'Granted job allocation \K[0-9]+')
@@ -40,9 +51,9 @@ fi
 
 srun --jobid=$JOB_ID \
 --container-image=$CONTAINER_IMAGE \
---container-mounts=$GITHUB_WORKSPACE:/workspace/,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
+--container-mounts=$GITHUB_WORKSPACE:$CONTAINER_MOUNT_DIR,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
 --container-mount-home \
---container-workdir=/workspace/ \
+--container-workdir=$CONTAINER_MOUNT_DIR \
 --no-container-entrypoint --export=ALL \
 bash benchmarks/single_node/${MODEL_CODE}_${PRECISION}_h200${FRAMEWORK_SUFFIX}${SPEC_SUFFIX}.sh
 
diff --git a/runners/launch_h200-nb.sh b/runners/launch_h200-nb.sh
index 9d157a858..fa8a9f7bb 100644
--- a/runners/launch_h200-nb.sh
+++ b/runners/launch_h200-nb.sh
@@ -9,14 +9,25 @@ SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
 
 PARTITION="main"
 
+# TODO(Cam): lmsysorg/sglang:deepseek-v4-hopper installs sglang editable at
+# /workspace/sglang/python (prior sglang tags used /sgl-workspace/sglang), so
+# the default $GITHUB_WORKSPACE:/workspace/ bind-mount masks the install and
+# breaks `import sglang`. Mount this one image at /ix instead; drop the
+# conditional once the image stops installing editable under /workspace.
+if [[ "$IMAGE" == *deepseek-v4-hopper* ]]; then
+    CONTAINER_MOUNT_DIR=/ix
+else
+    CONTAINER_MOUNT_DIR=/workspace
+fi
+
 set -x
 srun --partition=$PARTITION --gres=gpu:$TP --exclusive --job-name="$RUNNER_NAME" \
 --container-image=$IMAGE \
 --container-name=$(echo "$IMAGE" | sed 's/[\/:@#]/_/g')-${USER} \
---container-mounts=$GITHUB_WORKSPACE:/workspace/,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
+--container-mounts=$GITHUB_WORKSPACE:$CONTAINER_MOUNT_DIR,$HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \
 --container-remap-root \
 --container-writable \
 --container-mount-home \
---container-workdir=/workspace/ \
+--container-workdir=$CONTAINER_MOUNT_DIR \
 --no-container-entrypoint --export=ALL \
 bash benchmarks/single_node/${MODEL_CODE}_${PRECISION}_h200${FRAMEWORK_SUFFIX}${SPEC_SUFFIX}.sh