|
|
84b91750fb
|
fix: A1-14c run embedding model on Apple GPU via EMLX with EXLA-CPU fallback
|
2026-05-29 16:26:33 +02:00 |
|
|
|
61ff2a77c0
|
perf: A1-14b replace O(n^2) embedding snapshot with hnswlib HNSW index and debounced persistence
|
2026-05-29 15:36:13 +02:00 |
|
|
|
744f7543d7
|
perf: batch CPU embedding inference and add A1-14c Apple GPU (EMLX) spec gap
|
2026-05-29 14:43:39 +02:00 |
|
|
|
a1004d72bf
|
fix: A1-14 real neural embeddings via Bumblebee multilingual-e5-small with Float32 BLOB vector cache
|
2026-05-29 14:04:51 +02:00 |
|
|
|
fceb995c7c
|
chore: update allium spec for clearer wording towards embedding model
|
2026-05-28 22:21:36 +02:00 |
|
|
|
cd998f24a9
|
initial commit
Co-authored-by: Copilot <copilot@github.com>
|
2026-04-23 10:42:27 +02:00 |
|
