sglang dpskv4 hopper

.github/configs/nvidia-master.yaml

@@ -2510,6 +2510,27 @@ 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).
+dsv4-fp8-h200-sglang:
+  image: lmsysorg/sglang:deepseek-v4-hopper@sha256:7f19c6dc092e47a10fac2e41f47eab78970280d06648b8e50d312a82f0ae722f
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: h200
+  precision: fp8
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - 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

benchmarks/single_node/dsv4_fp8_h200_sglang.sh

@@ -0,0 +1,73 @@
+#!/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 $TP \
+    --moe-runner-backend marlin \
+    --chunked-prefill-size 4096 \
+    --disable-flashinfer-autotune \
+    --mem-fraction-static 0.88 \
+    --max-running-requests "$(( 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

runners/launch_h200-cw.sh

@@ -4,8 +4,13 @@ export HF_HUB_CACHE_MOUNT="/mnt/vast/gharunner/hf-hub-cache"
 export PORT=8888
 
 MODEL_CODE="${EXP_NAME%%_*}"
-FRAMEWORK_SUFFIX=$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt' || printf '')
 SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
+BENCH_BASE="benchmarks/single_node/${MODEL_CODE}_${PRECISION}_h200"
+BENCH_SCRIPT="${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
 
 PARTITION="h200"
 SQUASH_FILE="/mnt/vast/gharunner/squash/$(echo "$IMAGE" | sed 's/[\/:@#]/_/g').sqsh"
@@ -38,13 +43,19 @@ else
     CONTAINER_IMAGE=$(realpath $SQUASH_FILE)
 fi
 
+if [[ "$IMAGE" == *deepseek-v4-hopper* ]]; then
+    CONTAINER_MOUNT_DIR=/ix
+else
+    CONTAINER_MOUNT_DIR=/workspace
+fi
+
 srun --jobid=$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
+bash $BENCH_SCRIPT
 
 rmdir $SAGEMAKER_SHM_PATH
 scancel $JOB_ID

runners/launch_h200-dgxc-slurm.sh

@@ -286,13 +286,27 @@ else
         fi
     "
 
+    SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
+    BENCH_BASE="benchmarks/single_node/${EXP_NAME%%_*}_${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/${EXP_NAME%%_*}_${PRECISION}_h200$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt')$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp').sh
+        bash $BENCH_SCRIPT
 
     scancel $JOB_ID
 

runners/launch_h200-nb.sh

@@ -4,19 +4,31 @@ export HF_HUB_CACHE_MOUNT="/mnt/data/gharunners/hf-hub-cache/"
 export PORT=8888
 
 MODEL_CODE="${EXP_NAME%%_*}"
-FRAMEWORK_SUFFIX=$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt' || printf '')
 SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
 
+BENCH_BASE="benchmarks/single_node/${MODEL_CODE}_${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
+
 PARTITION="main"
 
 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
+bash $BENCH_SCRIPT