{"id":64292,"date":"2023-11-20T11:07:11","date_gmt":"2023-11-20T02:07:11","guid":{"rendered":"https:\/\/smilegate.ai\/?p=64292"},"modified":"2023-11-20T11:07:14","modified_gmt":"2023-11-20T02:07:14","slug":"llm%ec%9d%84-%eb%b9%a0%eb%a5%b4%ea%b2%8c-%ec%84%9c%eb%b9%99%ed%95%98%eb%8a%94-%eb%b0%a9%eb%b2%95","status":"publish","type":"post","link":"https:\/\/smilegate.ai\/cn\/2023\/11\/20\/llm%ec%9d%84-%eb%b9%a0%eb%a5%b4%ea%b2%8c-%ec%84%9c%eb%b9%99%ed%95%98%eb%8a%94-%eb%b0%a9%eb%b2%95\/","title":{"rendered":"LLM\uc744 \ube60\ub974\uac8c \uc11c\ube59\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

[\ubd84\uc11dAI\uc11c\ube44\uc2a4\ud300 \ubc15\ud6a8\uc8fc]<\/p>\n\n\n\n

\ucd5c\uadfc \uc5b8\uc5b4 \ubaa8\ub378\uc758 \ubc1c\uc804\uc740 \ud070 \uc784\ud329\ud2b8\ub97c \uc8fc\uc5c8\uace0, \uadf8\ub9cc\ud07c \uc5f0\uad6c \ub610\ud55c \ud65c\ubc1c\ud788 \uc774\ub8e8\uc5b4\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n

\n
\"\"
< “Language Model”, “Large Language Model”\uc744 \ud3ec\ud568\ud558\ub294 arXiv \ub17c\ubb38\uc758 \ub204\uc801 \uac1c\uc218 \ucd94\uc138[1] ><\/figcaption><\/figure><\/div>\n\n\n

\uadf8\ub7ec\ub098 \uc774\ub7ec\ud55c \ubaa8\ub378\uc758 \uc11c\ube59 \uacfc\uc815\uc5d0\uc11c \ubc1c\uc0dd\ud558\ub294 \uace0\ub3c4\uc758 \uacc4\uc0b0 \uc791\uc5c5\uacfc \uba54\ubaa8\ub9ac \uc694\uad6c\ub7c9\uc740 \uc0c8\ub85c\uc6b4 \ub3c4\uc804 \uacfc\uc81c\ub97c \uc81c\uc2dc\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ucd5c\uc801\ud654\ub41c \uc11c\ube59\uc740 \uc774\ub7ec\ud55c LLM\uc744 \ud6a8\uc728\uc801\uc73c\ub85c \uc6b4\uc601\ud558\uae30 \uc704\ud55c \uc911\uc694\ud55c \uc5ed\ud560\uc744 \uc218\ud589\ud569\ub2c8\ub2e4. \ubcf8\ubb38\uc5d0\uc11c\ub294 \uc774\ub7ec\ud55c \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud558\ub294 LLM \ucd5c\uc801\ud654 \ub77c\uc774\ube0c\ub7ec\ub9ac 3\uac1c\ub97c \uc18c\uac1c\ud569\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\ub77c\uc774\ube0c\ub7ec\ub9ac \uc18c\uac1c<\/h3>\n\n\n\n
<\/div>\n\n\n\n

FasterTransformer <\/strong>(GitHub<\/a>)<\/p>\n\n\n\n

\uac00\uc7a5 \uc720\uba85\ud55c \ubaa8\ub378 \ucd5c\uc801\ud654 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub85c LLM\uc774 \ub098\uc624\uae30 \uc804\ubd80\ud130 \uc0ac\uc6a9\ub418\ub2e4 LLM\uc774 \ub4f1\uc7a5\ud558\uba74\uc11c \ub354 \ub9ce\uc774 \uc0ac\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ud070 \ud2b9\uc9d5\uc740 C++, CUDA Native\ub85c \ub3d9\uc791\ud558\uace0 Model Parallel(Tensor Parallel\/Pipeline Parallel) \uae30\ubc18\uc758 \ucd94\ub860 \uac00\uc18d \uc5d4\uc9c4\uc744 \uad6c\ud604\ud588\ub2e4\ub294 \uac83\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n

\ub2e4\ub9cc 2023\ub144 \ucd08\uae4c\uc9c0 \ubc84\uc804\uc744 Release\ud558\ub2e4 \ud604\uc7ac\ub294 \uac1c\ubc1c\uc774 \uc911\ub2e8\ub418\uc5c8\uace0, \uc774\ud6c4 \uac1c\ubc1c \uac74\uc774 TensorRT-LLM\uc73c\ub85c \uc774\uad00\ub418\uc5c8\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

FasterTransformer\uc5d0\uc11c \uc9c0\uc6d0\ub418\ub294 \ubaa8\ub378\uc758 \uc885\ub958\ub294 \uc5ec\uae30<\/a>\uc11c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

vLLM<\/strong> (GitHub<\/a>)<\/p>\n\n\n\n

2023\ub144 6\uc6d4\uc5d0 \ub4f1\uc7a5\ud574\uc11c \ud604\uc7ac \uc778\uae30\uc788\ub294 \ubaa8\ub378 \ucd5c\uc801\ud654 \ub77c\uc774\ube0c\ub7ec\ub9ac \uc911 \ud558\ub098 \uc785\ub2c8\ub2e4. \ucc98\uc74c \ub4f1\uc7a5\ud588\uc744 \ub54c \uc9c0\uc6d0\ub418\ub294 \ubaa8\ub378\uc774 \ub9ce\uc9c0 \uc54a\uc558\ub358 FasterTransformer\uc5d0 \ube44\ud574 \ub2e4\uc218\uc758 \ucd5c\uc2e0 \ubaa8\ub378\uc744 \uc9c0\uc6d0\ud558\uba74\uc11c \ucd5c\uc2e0 \uc5b8\uc5b4 \ubaa8\ub378\ub4e4\uc744 \ud6a8\uc728\uc801\uc73c\ub85c \ub2e4\ub8f0 \uc218 \uc788\uac8c \ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ud070 \ud2b9\uc9d5\uc740 Paged Attention \uae30\ubc95\uc744 \ud65c\uc6a9\ud574\uc11c latency\ub97c \uc720\uc9c0\ud558\uba74\uc11c throughput\uc740 2-4X \ud5a5\uc0c1\ud588\ub2e4\ub294 \uac83\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n

vLLM\uc5d0\uc11c \uc9c0\uc6d0\ub418\ub294 \ubaa8\ub378\uc758 \uc885\ub958\ub294 \uc5ec\uae30<\/a>\uc11c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

TensorRT-LLM<\/strong> (GitHub<\/a>)<\/p>\n\n\n\n

\uac00\uc7a5 \ucd5c\uadfc\uc5d0 \uacf5\uac1c(2023\ub144 10\uc6d4)\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub85c, FasterTransformer\uc758 \ud6c4\uc18d \ubc84\uc804\uc785\ub2c8\ub2e4. \uc55e\uc5d0\uc11c \uc124\uba85\ub4dc\ub9b0 \uac83\ucc98\ub7fc FasterTransformer\uc758 \uac1c\ubc1c\uc774 \uc911\ub2e8\ub418\uace0 \uc774\ud6c4 \uae30\ub2a5\uc774 \ubaa8\ub450 TensorRT-LLM\uc5d0 \uc774\uad00 \uac1c\ubc1c\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ud070 \ud2b9\uc9d5\uc740 TensorRT \ub525\ub7ec\ub2dd \ucef4\ud37c\uc77c\ub7ec\uc640 \ucd5c\uc801\ud654\ub41c \ucee4\ub110, \uc804\/\ud6c4\ucc98\ub9ac \ub2e8\uacc4, Multi-GPU\/Multi-Node \ud1b5\uc2e0 \uae30\ubcf8\uc694\uc18c\uc5d0 In-flight Batching\uc774\ub77c \ubd88\ub9ac\ub294 \ucd5c\uc801\ud654\ub41c \uc2a4\ucf00\uc904\ub9c1 \uae30\uc220\uc774 \ud3ec\ud568\ub410\ub2e4\ub294 \uac83 \uc785\ub2c8\ub2e4.<\/p>\n\n\n\n

TensorRT-LLM\uc5d0\uc11c \uc9c0\uc6d0\ub418\ub294 \ubaa8\ub378\uc758 \uc885\ub958\ub294 \uc5ec\uae30<\/a>\uc11c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50<\/h3>\n\n\n\n

\ud65c\uc131\ud654 \ucd94\uc774 \ube44\uad50<\/strong><\/p>\n\n\n\n

\uc544\ub798 \uadf8\ub798\ud504\ub294 \uac01 \ub77c\uc774\ube0c\ub7ec\ub9ac \ubcc4 GitHub stars \ub204\uc801 \ucd94\uc774\uc785\ub2c8\ub2e4.<\/p>\n\n\n

\n
\"\"
< \ub77c\uc774\ube0c\ub7ec\ub9ac \ubcc4 GitHub Stars \ub204\uc801 \ucd94\uc774 ><\/figcaption><\/figure><\/div>\n\n\n

\uadf8\ub798\ud504\ub97c \ubcf4\uba74 FasterTransformer\uac00 \ucd9c\uc2dc\ub41c\uc9c0 \uc624\ub798\ub41c \ub9cc\ud07c \uafb8\uc900\ud55c \uc0c1\uc2b9\uc138\ub97c \ubcf4\uc774\uace0 \uc788\uace0, vLLM\uacfc TensorRT-LLM\uc774 \ub4f1\uc7a5\uacfc \ub3d9\uc2dc\uc5d0 \uae09\ub4f1\ud558\ub294 \uac83\uc744 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub97c \ubd10\ub3c4 vLLM\uacfc TensorRT-LLM\uc774 \uc5bc\ub9c8\ub098 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\uc778\uc9c0 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\uc9c0\uc6d0 \ubaa8\ub378 \ube44\uad50<\/strong><\/p>\n\n\n\n

\uac01 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc5d0\uc11c \uc9c0\uc6d0\ud558\ub294 \ubaa8\ub378\uc744 \ube44\uad50\ud574\ubcf4\uba74 \uc544\ub798 \ud45c\uc640 \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/th>FasterTransformer<\/strong><\/th>vLLM<\/strong><\/th>TensorRT-LLM<\/strong><\/th><\/tr><\/thead>
BLOOM<\/td>\u54e6<\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
GPT-J<\/td>\u54e6<\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
GPT-NeoX<\/td>\u54e6<\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
OPT<\/td>\u54e6<\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
GPT<\/td>\u54e6<\/td> <\/td>\u54e6<\/td><\/tr>
BERT<\/td>\u54e6<\/td> <\/td>\u54e6<\/td><\/tr>
T5<\/td>\u54e6<\/td> <\/td> <\/td><\/tr>
ViT<\/td>\u54e6<\/td> <\/td> <\/td><\/tr>
BART<\/td>\u54e6<\/td> <\/td> <\/td><\/tr>
DeBERTa<\/td>\u54e6<\/td> <\/td> <\/td><\/tr>
Aquila<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Baichuan<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
Falcon<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
GPT-2<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
StarCoder<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
SantaCoder<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
WizardCoder<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Dolly v2<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
StableLM<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
InternLM<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
LLaMA<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
LLaMA-2<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
Vicuna<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Alpaca<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Koala<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Guanaco<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Mistral<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
MPT<\/td> <\/td>\u54e6<\/td>\u54e6<\/td><\/tr>
Qwen<\/td> <\/td>\u54e6<\/td> <\/td><\/tr>
Blip2<\/td> <\/td> <\/td>\u54e6<\/td><\/tr>
ChatGLM-6B<\/td> <\/td>\uc608\uc815<\/td>\u54e6<\/td><\/tr>
ChatGLM2-6B<\/td> <\/td>\uc608\uc815<\/td>\u54e6<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

FasterTransformer<\/strong>\ub294 \uc62c \ucd08\uc5d0 \uac1c\ubc1c\uc744 \uc911\ub2e8\ud588\uae30 \ub54c\ubb38\uc5d0 \ucd5c\uc2e0 \ubaa8\ub378\uc740 \uc9c0\uc6d0\ub418\uc9c0 \uc54a\uc2b5\ub2c8\ub2e4. vLLM<\/strong>\uc740 \ub300\ubd80\ubd84\uc758 \ubaa8\ub378\uc744 \uc9c0\uc6d0\ud558\uba70 GLM \ubaa8\ub378\ub3c4 \uace7 \uc9c0\uc6d0\ub420 \uc608\uc815(v0.2.2<\/a>)\uc785\ub2c8\ub2e4. TensorRT-LLM<\/strong>\uc740 \uc9c0\uc6d0\uc774 \ub9ce\uc774 \uc548\ub418\ub294 \uac83\ucc98\ub7fc \ubcf4\uc774\uc9c0\ub9cc \ub300\ubd80\ubd84\uc758 \uae30\ubc18 \ubaa8\ub378\uc744 \uc9c0\uc6d0\ud558\uae30 \ub54c\ubb38\uc5d0 \ub300\ubd80\ubd84\uc758 \ubaa8\ub378\uc774 \uc9c0\uc6d0\ub41c\ub2e4\uace0 \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ub2e4\ub9cc \uc774 \ub54c\ubb38\uc5d0 \ubaa8\ub378\uc5d0 \ub300\ud574 \uc870\uae08\uc740 \uc774\ud574\ud558\uace0 \uc0ac\uc6a9\ud574\uc57c \ud560 \ud544\uc694\uac00 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\ucc98\ub9ac\ub7c9 \uc131\ub2a5 \ube44\uad50<\/strong><\/p>\n\n\n\n

\uac1c\ubc1c\uc774 \uc911\ub2e8\ub41c FasterTransformer\ub97c \uc81c\uc678\ud558\uace0 TensorRT-LLM\uacfc vLLM\uc758 \uc131\ub2a5\uc744 \ube44\uad50\ud55c \uacb0\uacfc\ub294 \uc544\ub798\uc640 \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n

\n
\"\"
< LLaMA-2-7b-hf \ubaa8\ub378\ub85c vLLM\uacfc TensorRT-LLM throughput \ube44\uad50[2] ><\/figcaption><\/figure><\/div>\n\n\n

Throughput\uc740 vLLM\uc774 \uc57d 130 tokens\/sec, TensorRT-LLM\uc774 \uc57d 120 tokens\/sec\uc73c\ub85c vLLM\uc774 \uc870\uae08 \ub354 \ucc98\ub9ac\ub7c9\uc774 \ub192\uc740 \uac83\uc744 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ud558\uc9c0\ub9cc \ud070 \ucc28\uc774\uac00 \uc788\ub294 \uac83\uc740 \uc544\ub2c8\uae30 \ub54c\ubb38\uc5d0 \uc0c1\ud669\uc5d0 \ub530\ub77c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc120\ud0dd\ud574\uc11c \uc0ac\uc6a9\ud574\ub3c4 \uad1c\ucc2e\uc744 \uac83 \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\ub9c8\uce68<\/h3>\n\n\n\n

LLM \uc5f0\uad6c\uac00 \ud65c\ubc1c\ud788 \uc774\ub8e8\uc5b4\uc9c0\uace0 \uc788\ub294 \ub9cc\ud07c \ubaa8\ub378\uc758 \ucd5c\uc801\ud654 \ub610\ud55c \ud544\uc694\ud558\ub2e4\ub294 \uac83\uc744 \ub77c\uc774\ube0c\ub7ec\ub9ac \ubcc4 GitHub stars \ub204\uc801 \ucd94\uc774\ub9cc \ubd10\ub3c4 \uc54c \uc218 \uc788\uc2b5\ub2c8\ub2e4. vLLM \ud639\uc740 TensorRT-LLM\uc744 \uc0ac\uc6a9\ud588\uc744 \ub54c\uc758 \ud6a8\uacfc\ub294 \ud655\uc2e4\ud558\uc9c0\ub9cc, \ub450 \ub77c\uc774\ube0c\ub7ec\ub9ac \ubaa8\ub450 \uc544\uc9c1 \ucd08\uae30 \ubc84\uc804\uc774\uae30 \ub54c\ubb38\uc5d0 \uc0ac\uc6a9\ud560 \ub54c \uc0c8\ub85c Release\ub418\ub294 \ubc84\uc804\uc758 \uae30\ub2a5\uc744 \uc0b4\ud3b4\ubcf4\uba74\uc11c \ud310\ub2e8\ud560 \ud544\uc694\uac00 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

<\/div>\n\n\n\n

\u53c2\u8003<\/strong><\/p>\n\n\n\n

[1] Zhao, Wayne Xin, et al. “A survey of large language models.” arXiv preprint arXiv:2303.18223 (2023).
[2] https:\/\/twitter.com\/HamelHusain\/status\/1719872352694174093
[3] https:\/\/developer.nvidia.com\/blog\/optimizing-inference-on-llms-with-tensorrt-llm-now-publicly-available\/
<\/p>\n

<\/span><\/div>","protected":false},"excerpt":{"rendered":"

[\ubd84\uc11dAI\uc11c\ube44\uc2a4\ud300 \ubc15\ud6a8\uc8fc] \ucd5c\uadfc \uc5b8\uc5b4 \ubaa8\ub378\uc758 \ubc1c\uc804\uc740 \ud070 \uc784\ud329\ud2b8\ub97c \uc8fc\uc5c8\uace0, \uadf8\ub9cc\ud07c \uc5f0\uad6c \ub610\ud55c \ud65c\ubc1c\ud788 \uc774\ub8e8\uc5b4\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774\ub7ec\ud55c \ubaa8\ub378\uc758 \uc11c\ube59 \uacfc\uc815\uc5d0\uc11c \ubc1c\uc0dd\ud558\ub294 \uace0\ub3c4\uc758 \uacc4\uc0b0 \uc791\uc5c5\uacfc \uba54\ubaa8\ub9ac \uc694\uad6c\ub7c9\uc740 \uc0c8\ub85c\uc6b4 \ub3c4\uc804 \uacfc\uc81c\ub97c \uc81c\uc2dc\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ucd5c\uc801\ud654\ub41c \uc11c\ube59\uc740 \uc774\ub7ec\ud55c LLM\uc744 \ud6a8\uc728\uc801\uc73c\ub85c \uc6b4\uc601\ud558\uae30 \uc704\ud55c \uc911\uc694\ud55c \uc5ed\ud560\uc744 \uc218\ud589\ud569\ub2c8\ub2e4. \ubcf8\ubb38\uc5d0\uc11c\ub294 \uc774\ub7ec\ud55c \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud558\ub294 LLM \ucd5c\uc801\ud654 \ub77c\uc774\ube0c\ub7ec\ub9ac 3\uac1c\ub97c \uc18c\uac1c\ud569\ub2c8\ub2e4. \ub77c\uc774\ube0c\ub7ec\ub9ac \uc18c\uac1c FasterTransformer (GitHub)…<\/p>\n

<\/span><\/div>","protected":false},"author":1,"featured_media":64309,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rank_math_lock_modified_date":false,"footnotes":""},"categories":[532,19],"tags":[667,713,714,715],"class_list":["post-64292","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-nlp","category-tech04","tag-llm","tag-fastertransformer","tag-vllm","tag-tensorrt-llm","category-532","category-19","description-off"],"_links":{"self":[{"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/posts\/64292","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/comments?post=64292"}],"version-history":[{"count":13,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/posts\/64292\/revisions"}],"predecessor-version":[{"id":64313,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/posts\/64292\/revisions\/64313"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/media\/64309"}],"wp:attachment":[{"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/media?parent=64292"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/categories?post=64292"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/smilegate.ai\/cn\/wp-json\/wp\/v2\/tags?post=64292"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}