lain on Nostr: still in awe how bad llama.cpp / ollama / vllm / lm studio / literally everything is. ...
still in awe how bad llama.cpp / ollama / vllm / lm studio / literally everything is. how can there still be a market for "good inference software that actually works"? who's gonna be the first?
Published at
2026-06-06 10:43:37 UTCEvent JSON
{
"id": "c4c066595f423139dc16b37f896a5983d139065415837fee636921e77a746e2e",
"pubkey": "653cd0a3f6e3f2c5ae4238cec6ce32f49c6aa6bf12dbde62475896fe0c1107f2",
"created_at": 1780742617,
"kind": 1,
"tags": [
[
"proxy",
"https://fediffusion.art/objects/dbc5ea7d-6561-4f37-806f-cfa77fc29825",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "still in awe how bad llama.cpp / ollama / vllm / lm studio / literally everything is. how can there still be a market for \"good inference software that actually works\"? who's gonna be the first?",
"sig": "504176e4210789825a58ae0e9278b66423e6d06528d4c83c5adcd92baf70e072af9d2941f6f9f42c66920a628ff7fb77da2065f183fecd6a9c400b5fd83ffadd"
}
