Richard Loyer
6935089459
dist: libkazeia_engine.so rebuild option C (paquet cohérent), notes rebuild MAJ
...
libkazeia_engine.so reconstruit depuis le JNI option C (37KB strippé, 4 symboles JNI, SHARED,
NEEDED llama/ggml/ggml-base/log/c++_shared). Le paquet dist/ est désormais interne-cohérent:
sources + prebuilts alignés (option C + fix SSM_CONV). Docs: prebuilts à jour, rebuild app-side
recommandé pour ABI/STL. Logique validée via dual_ctx_mt (JNI non testé via Java ici).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 10:45:47 +02:00
Richard Loyer
2699b631a3
dist: prefill HTP corrigé (SSM_CONV gate backend), JNI option C sans OPFILTER
...
Fix intégré dans libggml-hexagon.so (ql e872623): ggml_hexagon_supported_ssm_conv route le
conv1d multi-token (prefill) sur ggml-cpu (le kernel HTP est faux multi-token pour d_inner
1024/2048). Plus besoin de GGML_HEXAGON_OPFILTER -> retiré du JNI. Validé: oracle SSM_CONV 18/18,
cli -dev HTP0 cohérent, multi-tour cohérent+mémoire, prefill HTP 110-180 t/s. libggml-hexagon.so
rafraîchi. Rebuild requis avant ship: libggml-hexagon.so + libkazeia_engine.so. Docs MAJ.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 10:39:08 +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
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
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