Commit Graph

12 Commits

Author SHA1 Message Date
Richard Loyer fac50d69ce dist: bandeau HANDOFF source de vérité sur README/INTEGRATION (9B historique)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 23:34:15 +02:00
Richard Loyer 9417aba6cb dist: handoff intégration aligné décisions 26/05 (modèle q35-lmq4, perf, prompt)
HANDOFF.md = point d'entrée: modèle Speaker tranché = q35-lmq4 (éval qualité), 9B écarté,
kernel GDN clos. État JNI: config OK (t4/fa/thinking-off/greedy) MAIS CPU-only (ngl0) ->
2 décisions ouvertes documentées (prefill CPU vs HTP non câblé; KV q8_0 à revérifier, peut
coûter au decode). system_fr.txt = prompt prod (garde-fous 3114 + tutoiement + ne-pas-présumer,
correctifs issus de l'éval). MODELS/PERF/STATUS réalignés (decode 10.8, prefill 89.5 HTP capacité
mais JNI=CPU ~19, quant sous-Q4 morte). package.sh réassemble lib/ depuis ql/b.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 23:33:41 +02:00
Richard Loyer b2fc564f04 Engine sur fork qualcomm: decode dense 15.5>pte, 3.5 ~11, KVq8+t4+fa+lm_head-Q4; prefill 93/285; RAG cross 24-28k
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 15:53:14 +02:00
Richard Loyer 1252f32bd3 Rapport R&D complet: synthese session, perf, cascade, #277, briques, reste a faire
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 22:27:34 +02:00
Richard Loyer 9b62420089 v4 fix #277: ngl0 CPU decode 14tok/s, 4s/tour, usable 2026-05-25 10:18:31 +02:00
Richard Loyer 7a5780ca1d Bridge v3 utilisable: thinking-off ChatML, sys+usr, cap; static intact 2026-05-25 09:41:04 +02:00
Richard Loyer 76f21a21cb Bridge STATIC autonome (42MB): zero NEEDED partage, fix collision TTS libllama, valide device 2026-05-24 22:43:45 +02:00
Richard Loyer f877902903 STATUS.md: validé/limites pour integrateur 2026-05-24 22:17:42 +02:00
Richard Loyer c5c2738281 Valide device: generate() bout-en-bout OK (test_native), bridge pret integration 2026-05-24 22:05:44 +02:00
Richard Loyer 7dbf38db97 Doc complete: README+MODELS+PERF+PITFALLS, build nettoye 2026-05-24 21:59:56 +02:00
Richard Loyer 15b9baf6b2 JNI bridge complet: generate() prefill+decode, build arm64 OK (libkazeia_engine.so 209K) 2026-05-24 21:58:00 +02:00
Richard Loyer 0f92fa723f Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00