{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreihraorrredunu4mjhu4wpov2ckft2e43arw6e35eajus7fgniou2m",
"uri": "at://did:plc:nfto3lv2rcs5s7h7digotzlu/app.bsky.feed.post/3mqcseszfwl62"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreig7saeenw6c3prrms24e2bpcmq7mskq26az4ajg73ufx33cf4gf2a"
},
"mimeType": "image/png",
"size": 32236
},
"path": "/packages/fllamer",
"publishedAt": "2026-07-10T18:41:09.588Z",
"site": "https://pub.dev",
"textContent": "Mobile-first local llama.cpp inference, embeddings, RAG, multimodal, LoRA, and speculative decoding for Dart and Flutter. Changelog excerpt: - Prepared the package for warning-free pub.dev validation: vendored the curated pinned `llama.cpp`build sources, consolidated Dart CLIs under the conventional `example/`directory, and corrected published documentation paths and licensing metadata. - Added loaded-engine `tokenize`, `countTokens`, `detokenize`, `formatChat`, `countChatTokens`, and chat-template capability methods. They reuse the engine worker's existing model and serialize with inference; static chat token counting now formats an[...]",
"title": "v0.1.0 of fllamer",
"updatedAt": "2026-07-10T18:11:58.185Z"
}