Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
5 lines
1.7 KiB
Plaintext
5 lines
1.7 KiB
Plaintext
SERVER taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/vllm serve /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B --host 127.0.0.1 --port 8520 --served-model-name qwen3-30b-a3b-community --max-num-batched-tokens 8192 --max-num-seqs 8 --tensor-parallel-size 4 --shutdown-timeout 120
|
|
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py warmup --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016591107009 --tp 4 --mns 8 --base-url http://127.0.0.1:8520 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp4_mns8/warmup
|
|
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016591107009 --tp 4 --mns 8 --base-url http://127.0.0.1:8520 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp4_mns8/anchor-0.016591107009
|
|
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016055910008 --tp 4 --mns 8 --base-url http://127.0.0.1:8520 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp4_mns8/anchor-0.016055910008
|