15 lines
898 B
JSON
15 lines
898 B
JSON
{
|
|
"observation": "The incumbent should start from the exact known launch-safe qwen3.5-27b serving recipe on dash0 before asking the LLM to optimize throughput per GPU above that baseline.",
|
|
"diagnosis": "This model uses a long-context hybrid stack and fp8 quantization. The correct first measurement is to preserve the TP1 run_qwen27b.sh baseline exactly, then let later trials explore TP/DP and runtime knobs from that anchor.",
|
|
"config_patch": {
|
|
"env_patch": {},
|
|
"flag_patch": {}
|
|
},
|
|
"expected_effects": [
|
|
"Launch-safe TP1 baseline exactly aligned with run_qwen27b.sh",
|
|
"Reliable first incumbent for per-GPU comparison under the tighter TTFT and TPOT SLO",
|
|
"Clean anchor before topology exploration across TP*DP groups"
|
|
],
|
|
"why_not_previous_failures": "This baseline intentionally introduces no patch at all, so it cannot repeat previous tuning-only failures."
|
|
}
|