Yeah, it is really expensive to fully rent GPU server 😅
Do you utilized fully of your workstation GPU memory or still have some left?
Thanks for replicate suggestion. Yes, the price quite cheap if the request process run shortly. But, it seems I need "private model" to be setup on their service.
Based on your experience, did they calculate purely based on how long the request to be processed? Let's say we send request every second but the request only need 100ms to be processed, they calculate only those 100ms right?
Rif'at Ahdi R
npub19dn…wja7
2024-06-05 12:53:20
in reply to nevent1q…ymf2
Author Public Key
npub19dn7fq9hlxwjsdtgf28hyakcdmd73cccaf2u7a7vl42echey7ezs2hwja7Published at
2024-06-05 12:53:20Event JSON
{
"id": "02e51abdaea1ac3c00de5a651d0dd127a55b556dc255f746ff1e089a45cdc6e9",
"pubkey": "2b67e480b7f99d2835684a8f7276d86edbe8e318ea55cf77ccfd559c5f24f645",
"created_at": 1717584800,
"kind": 1,
"tags": [
[
"e",
"72ecea4a255874c630fe9bb0e5b683a42c7b3ddc42c0cd781efcbe9ec0682a51",
"",
"root"
],
[
"e",
"c5b0b38a8ac7908258d0f41b47905b5bd0f62379c7c77ded0351abe9ac6defcd"
],
[
"e",
"a4f0433d95e26f7fce428d3c181ba33a8d6eb7df8473324610a888f022af1838",
"",
"reply"
],
[
"p",
"99bb5591c9116600f845107d31f9b59e2f7c7e09a1ff802e84f1d43da557ca64"
],
[
"p",
"2b67e480b7f99d2835684a8f7276d86edbe8e318ea55cf77ccfd559c5f24f645"
]
],
"content": "Yeah, it is really expensive to fully rent GPU server 😅\n\nDo you utilized fully of your workstation GPU memory or still have some left?\n\nThanks for replicate suggestion. Yes, the price quite cheap if the request process run shortly. But, it seems I need \"private model\" to be setup on their service.\n\nBased on your experience, did they calculate purely based on how long the request to be processed? Let's say we send request every second but the request only need 100ms to be processed, they calculate only those 100ms right?",
"sig": "f2869788f9ea9927166ea08fee8848a17ebb90a14eb1deb04989b43205898ead6d3e2165232a28287d6867bce1cf3bc060a37e32fd1bf5e69502cab584e77192"
}