[NV] Add GLM-5 h200 sglang

.github/configs/nvidia-master.yaml

@@ -2020,6 +2020,28 @@ qwen3.5-fp8-h200-sglang:
     search-space:
     - { tp: 8, ep: 8, conc-start: 4, conc-end: 64 }
 
+glm5-fp8-h200-sglang:
+  image: lmsysorg/sglang:glm5-hopper
+  model: zai-org/GLM-5-FP8
+  model-prefix: glm5
+  runner: h200
+  precision: fp8
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+
 dsr1-fp8-h200-trt:
   image: nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2
   model: deepseek-ai/DeepSeek-R1-0528

benchmarks/single_node/glm5_fp8_h200.sh

@@ -0,0 +1,69 @@
+#!/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 $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+python3 -m sglang.launch_server \
+  --model-path "$MODEL" \
+  --host 0.0.0.0 \
+  --port "$PORT" \
+  --tp-size "$TP" \
+  --tool-call-parser glm47 \
+  --reasoning-parser glm45 \
+  --mem-fraction-static 0.85 \
+  --served-model-name glm-5-fp8 \
+  --trust-remote-code \
+  > "$SERVER_LOG" 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+# Server accepts glm-5-fp8 (--served-model-name); lm-eval must use that model name
+if [ "${RUN_EVAL}" = "true" ]; then
+    export MODEL_NAME=glm-5-fp8
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x

perf-changelog.yaml

@@ -970,3 +970,12 @@
     - "Replace old per-file recipes with resolved variants from consolidated 8k1k.yaml"
     - "14 variants: STP/MTP x low-latency/max-throughput with updated concurrencies and scale points"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/907
+
+- config-keys:
+    - glm5-fp8-h200-sglang
+  description:
+    - "Add GLM-5 FP8 SGLang H200 single-node benchmark"
+    - "Model: zai-org/GLM-5-FP8, image: lmsysorg/sglang:glm5-hopper"
+    - "Benchmark script: benchmarks/single_node/glm5_fp8_h200.sh"
+    - "Tool-call-parser glm47, reasoning-parser glm45, mem-fraction-static 0.85"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/914