Add decode-only study mode support
This commit is contained in:
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"observation": "This is the decode-only baseline directly aligned with run_qwen235b_decode.sh, including DecodeBenchConnector and the internal qwen3-235b launch shape.",
|
||||
"diagnosis": "A baseline measurement is required before proposing decode-only throughput changes. Preserve all current envs and flags to establish the first feasible sampling_u/request_rate point under the TPOT-only SLO.",
|
||||
"config_patch": {
|
||||
"env_patch": {},
|
||||
"flag_patch": {}
|
||||
},
|
||||
"expected_effects": [
|
||||
"Establish a launch-safe baseline for decode-only TPOT tuning",
|
||||
"Seed later trials from the first feasible sampling_u if one exists"
|
||||
],
|
||||
"why_not_previous_failures": "No previous failures in this study."
|
||||
}
|
||||
Reference in New Issue
Block a user