Kazeia
/
Kazeia-engine
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Kazeia-engine/dist
History
Richard Loyer 9b62420089 v4 fix #277: ngl0 CPU decode 14tok/s, 4s/tour, usable 2026-05-25 10:18:31 +02:00
..
include JNI bridge complet: generate() prefill+decode, build arm64 OK (libkazeia_engine.so 209K) 2026-05-24 21:58:00 +02:00
jni v4 fix #277: ngl0 CPU decode 14tok/s, 4s/tour, usable 2026-05-25 10:18:31 +02:00
lib Bridge v3 utilisable: thinking-off ChatML, sys+usr, cap; static intact 2026-05-25 09:41:04 +02:00
CMakeLists.txt JNI bridge complet: generate() prefill+decode, build arm64 OK (libkazeia_engine.so 209K) 2026-05-24 21:58:00 +02:00
INTEGRATION.md Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
MODELS.md Doc complete: README+MODELS+PERF+PITFALLS, build nettoye 2026-05-24 21:59:56 +02:00
PERF.md Doc complete: README+MODELS+PERF+PITFALLS, build nettoye 2026-05-24 21:59:56 +02:00
PITFALLS.md Doc complete: README+MODELS+PERF+PITFALLS, build nettoye 2026-05-24 21:59:56 +02:00
README.md v4 fix #277: ngl0 CPU decode 14tok/s, 4s/tour, usable 2026-05-25 10:18:31 +02:00
STATUS.md STATUS.md: validé/limites pour integrateur 2026-05-24 22:17:42 +02:00
TTS.md Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
llama-cli Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
test_engine Valide device: generate() bout-en-bout OK (test_native), bridge pret integration 2026-05-24 22:05:44 +02:00
test_native Valide device: generate() bout-en-bout OK (test_native), bridge pret integration 2026-05-24 22:05:44 +02:00
test_static Bridge STATIC autonome (42MB): zero NEEDED partage, fix collision TTS libllama, valide device 2026-05-24 22:43:45 +02:00
ts2 Bridge v3 utilisable: thinking-off ChatML, sys+usr, cap; static intact 2026-05-25 09:41:04 +02:00

README.md

Kazeia-Engine — intégration kazeia-android

Moteur LLM (+ TTS) GGUF, sans .pte, fork llama.cpp upstream + backend Hexagon. Remplace ExecuTorch/Genie pour le LLM. STT reste ORT-QAIRT (inchangé). Prefill NPU / decode CPU. Modèle dense (Qwen3) plein NPU ; hybride (Qwen3.5 DDDA) GDN sur NPU corrigé.

0. Périmètre

Brique Avant Après
LLM Speaker/Thinker ExecuTorch .pte Kazeia-Engine GGUF
TTS Talker/CP ggml-cpu engine (Talker prefill HTP option.)
TTS Decoder libtts_decoder_ggml inchangé
STT Whisper ORT-QAIRT inchangé

1. Contenu du paquet

  • lib/ : libkazeia_engine.so (bridge JNI) + libllama.so + libggml{,-base,-cpu,-hexagon}.so + libggml-htp-v68/69/73/75/79/81.so (sélection auto = V79 sur Pad3). 168 MB.
  • jni/ : kazeia_engine_jni.cpp, EngineLlmEngine.kt. include/, CMakeLists.txt.
  • INTEGRATION.md (steps), TTS.md, MODELS.md, PERF.md, PITFALLS.md.

2. Build (5 étapes)

  1. lib/*.so → kazeia-android/app/src/main/jniLibs/arm64-v8a/
  2. jni/kazeia_engine_jni.cpp → app/src/main/jni/, include/*.h à côté
  3. EngineLlmEngine.kt → com/kazeia/llm/, System.loadLibrary("kazeia_engine")
  4. CMake: lib avec libllama+libggml+libggml-base, -march=armv8.6-a+dotprod+fp16+i8mm+bf16
  5. GGUF → external storage, paths via KazeiaApplication.LLM_DIR

3. Cascade — remplace LlmProcessor cascade

Thinker Guard-4B → 4 bullets ; Speaker 9B = SYS_KAZEIA+bullets. Mono-moteur, reset() entre tours. Prompts: voir RAPPORT_KAZEIA §8. --reasoning-budget 0 impératif (sinon ramble anglais) : EngineLlmEngine met thinking off. Mesuré: 9B>4B qualité, Speaker=9B.

→ MODELS.md (choix), PERF.md (chiffres), PITFALLS.md (params_fit, no tty, OOM 30B+), INTEGRATION.md (détail API). API: load/generate/reset/free.

VALIDÉ DEVICE 24/05

test_native (=logique generate bridge) sur Pad3: load 4B HTP+decode CPU+detok = OUT propre, exit0. Pipeline prefill-NPU/decode-CPU prouve end-to-end. dist/jni/test_native.cpp = harness reproductible. Bridge so: 4 symboles JNI + deps ok. Reste app: gradle+jniLibs+template chat.

v2 STATIC (collision libllama TTS resolue)

TTS Talker/CP linke vs son libllama.so -> conflit ABI. FIX: libkazeia_engine.so STATIC (llama+ggml+ggml-cpu+hexagon en .a, --whole-archive hexagon). NEEDED= libm/log/dl/c only, 42MB. Coexiste avec libllama TTS. Drop: libkazeia_engine.so + libggml-htp-v79.so. Valide device 4B HTP. Build: bstatic BUILD_SHARED_LIBS=OFF.

v3 utilisable: thinking-off bridge

generate(sys,usr,max): wrap ChatML + vide = stop reasoning, decode 4B 15tok/s ~5s/tour. test 4B: "Je suis desole..." 40s(load)+gen. signature 2-arg. cap maxTok 64. dist=libkazeia_engine.so static + htp-v79. #277 fix livre.

v4 USABLE: ngl0 CPU decode (vrai fix #277)

Hang in-app=0.21tok/s: ngl99 -> decode ping-pong NPU/GDN-CPU. FIX: n_gpu_layers=0 decode CPU pur 14tok/s. test 4B: reponse FR 4s/tour. dev avait raison: pas thinking. cap64 garde. Speaker=4B CPU ngl0. RAM 4.5G. dist=libkazeia_engine.so. utilisable, #277 debloque.