Test ordered one-slot DFlash2 placements and preserve results
This commit is contained in:
1 parent
3d5931146b
commit
4007242709
25 files changed
+360
-5
No files matched your search
@@ -0,0 +1,19 @@
|
||||
[
|
||||
{
|
||||
"label": "medium-slot1-priority2-draft-cuda1",
|
||||
"model": "pure",
|
||||
"ctx": 160000,
|
||||
"single": false,
|
||||
"split": "80,20",
|
||||
"ubatch": 128,
|
||||
"parallel": 1,
|
||||
"draft_max": 7,
|
||||
"draft_kv": "q4_0",
|
||||
"draft_device": "CUDA1",
|
||||
"quality": false,
|
||||
"prompts": [
|
||||
4096
|
||||
],
|
||||
"minimum_headroom_mib": 512
|
||||
}
|
||||
]
|
||||
Reference in new issue
Block a user