EngineX-Mthreads/enginex-mthreads-vllm
4
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
luopingyi
2026-01-09 13:34:11 +08:00
parent dfa6476b58
commit b2ef04d792
538 changed files with 105693 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
tests/fp8_kv/llama2-7b-fp8-kv/kv_cache_scales.json Normal file
View File

@@ -0,0 +1,42 @@
{
"model_type": "llama",
"kv_cache": {
"dtype": "float8_e4m3fn",
"scaling_factor": {
"0": {
"0": 0.0152239128947258,
"1": 0.0188860222697258,
"2": 0.0354178324341774,
"3": 0.0376674123108387,
"4": 0.0418526791036129,
"5": 0.0433175228536129,
"6": 0.0397600457072258,
"7": 0.0424455925822258,
"8": 0.0415387861430645,
"9": 0.0408412404358387,
"10": 0.0395856611430645,
"11": 0.0377371683716774,
"12": 0.0400739423930645,
"13": 0.040771484375,
"14": 0.0393415205180645,
"15": 0.0369001142680645,
"16": 0.03857421875,
"17": 0.0387486070394516,
"18": 0.0403180830180645,
"19": 0.0396205373108387,
"20": 0.0375627800822258,
"21": 0.0407366082072258,
"22": 0.0432477705180645,
"23": 0.0377022884786129,
"24": 0.0399693101644516,
"25": 0.0374581478536129,
"26": 0.0413295216858387,
"27": 0.0442243330180645,
"28": 0.0424804724752903,
"29": 0.0456891767680645,
"30": 0.0409109964966774,
"31": 0.0482352152466774
}
}
}
}