# GLM-5.3-NVFP4 TP4PP2 profile 实验配置(174.1.60.5, 2026-09-06) HOST=174.1.60.5 MODEL=/data/hf_models/GLM-5.3-NVFP4 IMAGE=lmsysorg/sglang:nightly-dev-20260828-daf63171 CONTAINER=glm53-nvfp4 PORT=30000 # 部署(与 09-05 获胜配置逐字一致) DEPLOY="bash /root/deploy_par.sh --tp 4 --pp-size 2 --disable-overlap-schedule --max-prefill-tokens 16384 nomtp" EXTRA_SERVER_DEFAULTS="kv fp8_e4m3 auto; --disable-shared-experts-fusion --moe-runner-backend flashinfer_cutlass --disable-flashinfer-autotune; hicache-ratio 3; mem-frac 0.88; chunked-prefill 8192" # 采集 PROFILER=sglang /start_profile (CPU+GPU, no stack; with_stack 在本 nightly 病态禁用) TRACE_BASE=/data/hf_models/pp2tp4_profiles SCENARIOS=A_prefill(16x16384->1 cc16), B_decode(16x16384->512 cc16, 60 steps), D_128k(8x131072 cc8, 90% shared, 16 steps), E_nccl_simple(16k probe x2 fwd) # 基准(干净无 profiler,seed 每轮更换) BENCH_CC16="python3 -m sglang.bench_serving --backend sglang --dataset-name random-ids --num-prompts 16 --random-input-len 16384 --random-output-len 512 --max-concurrency 16 --temperature 0.0 --flush-cache --warmup-requests 1" BASELINE_CLEAN="input 3350 tok/s; output 104.7 tok/s; TTFT 31.36s; TPOT 50.87ms"