[NV] Add deepseek-v4-pro b300 vllm config

.github/configs/nvidia-master.yaml

@@ -2448,6 +2448,34 @@ dsv4-fp8-h200-vllm:
     search-space:
     - { tp: 8, ep: 8, dp-attn: true, 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
+# layouts on 4 allocated GPUs.
+dsv4-fp4-b300-vllm:
+  image: vllm/vllm-openai:deepseekv4-cu130
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: b300
+  precision: fp4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 4 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 8, conc-start: 128, conc-end: 128 }
+    - { tp: 4, dp-attn: true, conc-start: 256, conc-end: 512 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 4 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 8, conc-start: 128, conc-end: 128 }
+    - { tp: 4, dp-attn: true, conc-start: 256, conc-end: 512 }
+
 qwen3.5-fp8-h200-sglang:
   image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: Qwen/Qwen3.5-397B-A17B-FP8

benchmarks/single_node/dsv4_fp4_b300_vllm.sh

@@ -0,0 +1,104 @@
+#!/usr/bin/env bash
+
+# DeepSeek-V4-Pro B300 single-node aggregate recipe from the submitted B300
+# pareto sweep. The matrix uses dp-attn=true as the existing switch to flip a
+# 4-GPU run from TP4 to DP4. Expert parallel is always enabled to match the
+# provided vllm serve command exactly.
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    DP_ATTENTION \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# DeepSeek-V4-Pro weights are large; engine startup can exceed the default
+# 600s. Give it an hour to load.
+export VLLM_ENGINE_READY_TIMEOUT_S=3600
+
+PARALLEL_ARGS=(--tensor-parallel-size "$TP" --data-parallel-size 1)
+if [ "${DP_ATTENTION}" = "true" ]; then
+    PARALLEL_ARGS=(--tensor-parallel-size 1 --data-parallel-size "$TP")
+fi
+
+BENCHMARK_MAX_MODEL_LEN="$MAX_MODEL_LEN"
+if [ "$ISL" -eq 1024 ] && [ "$OSL" -eq 1024 ]; then
+    BENCHMARK_MAX_MODEL_LEN=4096
+fi
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    EVAL_MAX_MODEL_LEN=$(compute_eval_context_length "$MODEL" "$BENCHMARK_MAX_MODEL_LEN")
+    export EVAL_MAX_MODEL_LEN
+    SERVE_MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN"
+else
+    SERVE_MAX_MODEL_LEN="$BENCHMARK_MAX_MODEL_LEN"
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+vllm serve "$MODEL" --host 0.0.0.0 --port "$PORT" \
+    "${PARALLEL_ARGS[@]}" \
+    --pipeline-parallel-size 1 \
+    --kv-cache-dtype fp8 \
+    --trust-remote-code \
+    --block-size 256 \
+    --no-enable-prefix-caching \
+    --enable-expert-parallel \
+    --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}' \
+    --attention_config.use_fp4_indexer_cache True \
+    --tokenizer-mode deepseek_v4 \
+    --tool-call-parser deepseek_v4 \
+    --enable-auto-tool-choice \
+    --reasoning-parser deepseek_v4 \
+    --max-cudagraph-capture-size 2048 \
+    --max-model-len "$SERVE_MAX_MODEL_LEN" \
+    --max-num-batched-tokens 2048 > "$SERVER_LOG" 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$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 /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x

perf-changelog.yaml

@@ -1755,7 +1755,7 @@
     - "VLLM_ENGINE_READY_TIMEOUT_S=3600 to accommodate large weight loading"
     - "Configs: 1k1k conc 4-64, 8k1k conc 4-64"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1130
-  
+
 - config-keys:
     - dsv4-fp4-b300-sglang
   description:
@@ -1766,3 +1766,14 @@
     - "Prefix caching disabled, no speculative decoding"
     - "Configs: 1k1k conc 4-1024, 8k1k conc 4-512"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1143
+
+- config-keys:
+    - dsv4-fp4-b300-vllm
+  description:
+    - "Add DeepSeek-V4-Pro single-node B300 vLLM aggregate benchmark"
+    - "Image: vllm/vllm-openai:deepseekv4-cu130"
+    - "Model: deepseek-ai/DeepSeek-V4-Pro"
+    - "Uses the submitted B300 pareto schedule for both 1k1k and 8k1k, excluding conc 1: TP8 at conc 4/128, TP4 at conc 4/8/16/32/64/128, DP4 at conc 256/512"
+    - "Launch args match the provided vllm serve command, including FP4 indexer cache, FULL_AND_PIECEWISE cudagraph config, and max-num-batched-tokens 2048"
+    - "1k1k uses --max-model-len 4096; 8k1k uses the workflow-provided benchmark context length"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1144

runners/launch_b300-nv.sh

@@ -259,7 +259,11 @@ else
         export MODEL="$HF_HUB_CACHE_MOUNT/dsv4-pro"
     fi
     SQUASH_FILE="/data/home/sa-shared/gharunners/squash/$(echo "$IMAGE" | sed 's/[\/:@#]/_/g').sqsh"
-    FRAMEWORK_SUFFIX=$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt' || printf '')
+    if [[ "$MODEL_PREFIX" == "dsv4" ]]; then
+        FRAMEWORK_SUFFIX="_${FRAMEWORK}"
+    else
+        FRAMEWORK_SUFFIX=$([[ "$FRAMEWORK" == "trt" ]] && printf '_trt' || printf '')
+    fi
     SPEC_SUFFIX=$([[ "$SPEC_DECODING" == "mtp" ]] && printf '_mtp' || printf '')
     LOCK_FILE="${SQUASH_FILE}.lock"