Document MTP 2 speed and memory tradeoff; retain stable default
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"graph": {
|
||||
"decode_tps_median": 77.11544284916513,
|
||||
"ttft_median": 0.06954390600003535,
|
||||
"reasoning_tokens": [
|
||||
212,
|
||||
212,
|
||||
212
|
||||
]
|
||||
},
|
||||
"mtp2": {
|
||||
"decode_tps_median": 148.54509325898877,
|
||||
"ttft_median": 0.08631457799947384,
|
||||
"reasoning_tokens": [
|
||||
247,
|
||||
247,
|
||||
247
|
||||
]
|
||||
},
|
||||
"speedup": 1.9262690814022467,
|
||||
"identical_output": false,
|
||||
"min_host_available_gib": 171.57903671264648,
|
||||
"max_oom_kill": 0,
|
||||
"safeguard_triggered": false
|
||||
}
|
||||
Reference in New Issue
Block a user