f68ecb4573
- LlmLoader.kt : chargeur agnostique (magic-byte GGUF/ET12), interface LlmEngine, GgufLlmEngine (CPU-i8mm, hybride Qwen3.5-4B) + PteLlmEngine (NPU, denses). - LLM_INTEGRATION.md : doc dev complète (modeles, perf mesuree, integration, SELinux no-root, export .pte) ; remplace la v02/06 perimee (GGUF+ggml-hexagon). - .pte denses prepares+valides on-device : Qwen3-4B 15.7 / Qwen3-8B 10.5 / Guard-4B 17.2 / Qwen2.5-7B 8.0 tok/s ; wrapper JNI libkazeia_pte parite bit-exacte. - BUG_pte_inapp_qnn_version_mismatch.md : diag in-app err 5010 = backend QNN != 2.42 (pas le .pte) ; ancien rapport overflow int32 retracte (refute par test CLI 8B). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| b-jni | ||
| b-jni-cpu | ||
| cosyvoice | ||
| decoder_patches | ||
| distill | ||
| include | ||
| jni | ||
| lib | ||
| lib-cpu | ||
| outetts | ||
| patches | ||
| scripts | ||
| BUG_pte_inapp_qnn_version_mismatch.md | ||
| BUG_pte_multicontext_offset_overflow.md | ||
| CMakeLists.txt | ||
| HANDOFF.md | ||
| INTEGRATION.md | ||
| KAZEIA_ENGINE_OVERVIEW.md | ||
| LLM_INTEGRATION.md | ||
| MODELS.md | ||
| PATCH_QNN_PROD.md | ||
| PERF.md | ||
| PERF_ANALYSIS.md | ||
| PERF_CPU_OPTIMS.md | ||
| PERF_INFRA_TESTS.md | ||
| PERF_VULKAN_TESTS.md | ||
| PITFALLS.md | ||
| RAG_INTEGRATION.md | ||
| README.md | ||
| REBUILD_CPU_ONLY.md | ||
| STATUS.md | ||
| STT_INTEGRATION.md | ||
| TTS.md | ||
| TTS_INTEGRATION.md | ||
| build_decoder_subproc.sh | ||
| build_ggml_vulkan.sh | ||
| build_kazeia_stt.sh | ||
| build_kazeia_tts.sh | ||
| build_speaker_encoder.sh | ||
| build_stt_cli.sh | ||
| build_stt_test.sh | ||
| build_test_engine_2calls.sh | ||
| build_test_tokenizer.sh | ||
| build_tts_pipeline.sh | ||
| build_tts_pipeline_chraac.sh | ||
| llama-cli | ||
| package.sh | ||
| system_fr.txt | ||
| test_native | ||
README.md
⚠ Source de vérité à jour = HANDOFF.md (26/05). Modèle tranché =
q35-lmq4(Qwen3.5-4B), 9B écarté. Les mentions de 9B/cascade ci-dessous sont historiques.
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)
lib/*.so→kazeia-android/app/src/main/jniLibs/arm64-v8a/jni/kazeia_engine_jni.cpp→app/src/main/jni/,include/*.hà côtéEngineLlmEngine.kt→com/kazeia/llm/,System.loadLibrary("kazeia_engine")- CMake: lib avec libllama+libggml+libggml-base,
-march=armv8.6-a+dotprod+fp16+i8mm+bf16 - 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.