43 lines
1.8 KiB
JSON
43 lines
1.8 KiB
JSON
{
|
|
"schema": "aituner-tuning-cost-v1",
|
|
"year": 2026,
|
|
"task": {
|
|
"model": "Qwen/Qwen3-30B-A3B",
|
|
"engine": "community-vLLM 0.20.0",
|
|
"gpu": "NVIDIA H20",
|
|
"trace_window": "chat_w20260311_1000",
|
|
"input_tokens": [0, 8192],
|
|
"output_tokens": 128,
|
|
"replay_time_scale": 0.1,
|
|
"target_pass_rate": 0.95,
|
|
"ttft_ms": [2000, 4000, 6000],
|
|
"tpot_ms": 50
|
|
},
|
|
"sequential_runs": {
|
|
"pure_llm": {
|
|
"root": "ssh://dash0/home/admin/cpfs/wjh/aituner/aituner/.aituner-community-vllm020/dash0-qwen30b-a3b-community-vllm020-chat-0-8k-out128-scale01-high1-noharness",
|
|
"expected_trials": 12,
|
|
"missing_log_duration_s": {
|
|
"trial-0003": 13.0
|
|
},
|
|
"missing_log_reason": {
|
|
"trial-0003": "conservative trial_spec-to-result mtime envelope for a pre-ready CLI failure"
|
|
}
|
|
},
|
|
"guided_harness": {
|
|
"root": "ssh://dash0/home/admin/cpfs/wjh/aituner/aituner/.aituner-community-vllm020/dash0-qwen30b-a3b-community-vllm020-chat-0-8k-out128-scale01-high1-harness-guided-v2",
|
|
"expected_trials": 4,
|
|
"missing_log_duration_s": {},
|
|
"missing_log_reason": {}
|
|
}
|
|
},
|
|
"real_surface": {
|
|
"primary_root": "recovered-stores/aituner-interaction-runs-dash1-20260710/interaction-mixed-qwen30b-tp-mns-surface-high1-dash1-d8899c5-20260701T095858Z/store/interaction-mixed-qwen30b-tp-mns-surface-high1-dash1-d8899c5-20260701T095858Z",
|
|
"tp4_companion_root": "recovered-stores/aituner-interaction-runs-dash1-20260710/interaction-mixed-qwen30b-tp4-mns-nocap-qps20-dash1-d8899c5-20260701T161900Z/store/interaction-mixed-qwen30b-tp4-mns-nocap-qps20-dash1-d8899c5-20260701T161900Z",
|
|
"expected_cells": 12,
|
|
"fixed_max_num_batched_tokens": 8192
|
|
},
|
|
"simulator_metrics": "/home/gahow/phd/replayserve/runs/simfid_s2rb/results/metrics.json",
|
|
"threshold_regrets": [0.05, 0.02, 0.01, 0.0]
|
|
}
|