[Simulator] Add high-fidelity CPU-based inference simulator (#33824)

Co-authored-by: zhouhaizhu.zhz <zhouhaizhu.zhz@alibaba-inc.com>
Co-authored-by: LinSiyuan814 <linsiyuan.lsy@alibaba-inc.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
This commit is contained in:
Ruiyan Ma
2026-09-04 11:12:11 +08:00
committed by GitHub
co-authored by zhouhaizhu.zhz LinSiyuan814 hzh0425
parent a5f07b1241
commit 59799a3687
81 changed files with 6624 additions and 0 deletions
@@ -0,0 +1,59 @@
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[UNK]": 0,
"prefix": 1,
"caching": 2,
"latency": 3,
"decode": 4,
"token": 5
},
"unk_token": "[UNK]"
}
}
@@ -0,0 +1,6 @@
{
"backend": "tokenizers",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "TokenizersBackend",
"unk_token": "[UNK]"
}