Kazeia
/
Kazeia-engine
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
50 Commits 1 Branch 0 Tags 217 MiB
Commit Graph

35 Commits

Author SHA1 Message Date
Richard Loyer 025bdd87bd Briques: 2B 13, 4B 7, 9B 2.1; 2B sweet spot 2026-05-25 18:34:16 +02:00
Richard Loyer cbc379f9e5 Chiffres stables r3: 4B 9.8 9B 5.2 (r1 etaient bruit); engine tient, pte 4B devant 2026-05-25 17:41:08 +02:00
Richard Loyer 8cc9286f70 Correction: 9B CPU ~4.4 (t8 contention), <8B pte; 4B seul GGUF viable 2026-05-25 15:54:46 +02:00
Richard Loyer e462d7ce27 9B cible: 1-coeur in-app=0.16, t8=8.4; pte8B repli; merge=affinity 8 coeurs 2026-05-25 13:04:21 +02:00
Richard Loyer 7aae1f5fc7 Final: pte 4B 15/2.2GB > GGUF 0.32; merge=t8 mais pte reste mieux 4B; gguf utile=gros modeles 2026-05-25 12:21:04 +02:00
Richard Loyer cdb34a65f1 0.32 = 1 thread + HTP residuel; fix t8+ngl0 = 14tok/s 2026-05-25 11:18:38 +02:00
Richard Loyer 23f2c9fcfc #277: dist=static ngl0 OK; crash dev=stale shared so + ancienne signature 1-arg 2026-05-25 10:44:53 +02:00
Richard Loyer fe6826a3be Integration #277: hang=thinking non bride, fix budget0+cap; 4B>9B CPU 2026-05-25 09:38:25 +02:00
Richard Loyer 9675280760 GDN chunkwise: HMX fp16 bloque bit-exact, HVX qf32 3-5sem; reste 55/15 CPU exact 2026-05-24 22:12:47 +02:00
Richard Loyer 1a6637bd67 TTS: Talker GGUF chargeable, audio e2e=JNI app non valide shell; GDN agent en cours 2026-05-24 22:12:23 +02:00
Richard Loyer 1024167bdc Empreinte: engine GGUF 2.4/5.0 vs pte 3.3/5.9, -15-30% 2026-05-24 21:18:16 +02:00
Richard Loyer 9f7bc1e6c3 Comparatif FR: 9B>4B (psy juste vs derive role), engine OK budget0 2026-05-24 21:12:10 +02:00
Richard Loyer 431865f07f Fix cascade: reasoning-budget 0 (engine OK, FR coherent); A/B = JNI 2026-05-24 20:15:41 +02:00
Richard Loyer 25b1344c19 Cmp 4B/9B: 9B+riche, mais eval FR shell impossible, requiert JNI 2026-05-24 19:50:24 +02:00
Richard Loyer db6c063705 Cascade 9B+Guard4B/8B: speed+RAM mesures, reco Guard4B; eval texte = JNI 2026-05-24 19:30:56 +02:00
Richard Loyer 7f9dda4a75 Cascade 9B+Guard4B tient (7.5GB), Guard8B ok aussi; verdict gros modeles 2026-05-24 19:21:08 +02:00
Richard Loyer f82fa61281 9B: 41/8.4 5GB tient; 30B/35B OOM. Plafond=9B+4B parallele, MoE hors-jeu 2026-05-24 19:13:20 +02:00
Richard Loyer 47e75d74a4 Prefill cap = recurrence serielle, HVX inutile; gain=chunkwise GDN matriciel (weeks) 2026-05-24 18:55:49 +02:00
Richard Loyer e1a6d4e764 Prefill: HMX/batch satures, GDN scalaire ancre, plafond ~103 via HVX chunkwise 2026-05-24 18:29:46 +02:00
Richard Loyer ce5d91946e Comparatif: Q3-4B 103/17, Q3.5-4B 55/15, ExecuTorch 14-21. Engine egale decode sans pte 2026-05-24 18:19:27 +02:00
Richard Loyer eb72df4767 Mesure split ref: prefill HTP 55 / decode CPU 15 Qwen3.5-4B, end-to-end ~13s 2026-05-24 18:08:39 +02:00
Richard Loyer 1b64bbb7eb Clarif: gen lente = decode-NPU cli, pas GDN; split prefill-NPU/decode-CPU = role JNI 2026-05-24 18:06:40 +02:00
Richard Loyer 104c6b4ad5 CLAUDE: chantier1 clos 2026-05-24 17:16:44 +02:00
Richard Loyer 17a78f1c6a Profil: GDN absent HTP (100% CPU confirme), CONT+SSM_CONV+MULMAT dominent; lib restauree 2026-05-24 16:53:08 +02:00
Richard Loyer 3a5f735ab9 Optim prefill: ngl99/t8/b512=49.9 t/s (+11%), full offload, decode CPU 2026-05-24 16:35:52 +02:00
Richard Loyer 627f9a80e2 Correctif: OPFILTER inexistant, isolation GDN_cpu = bench DEBUG; bugs+qualite requalifies 2026-05-24 15:58:18 +02:00
Richard Loyer d05483b13a Bug cli = overflow buffer HTP gros prefill (2^44), pas init; qualite 4B OK 2026-05-24 15:52:33 +02:00
Richard Loyer 753d8be2b0 pp1024 plat (saturation batchable), bornes GDN: cout B-2 non mesure, profiler bloque par cli 2026-05-24 15:44:45 +02:00
Richard Loyer 4dd863ecb5 Verdict: GDN HTP decode-only (2284), prefill GDN fallback CPU = ancre. B chiffre. 2026-05-24 14:49:39 +02:00
Richard Loyer eceacaba9a Mesures 4B: HTP prefill 44 / CPU decode 13.4, qwen35_compile HTP fonctionne 2026-05-24 14:33:17 +02:00
Richard Loyer 2779babcab Rebuild upstream+hexagon: configure OK (NDK r27d, SDK 6.5, v79), build lance 2026-05-24 13:01:16 +02:00
Richard Loyer 6aa4d06c95 Ambition haute: cible = Qwen3.5-4B near-ExecuTorch, prefill GDN sur HTP, decode CPU 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-24 12:57:37 +02:00
Richard Loyer 12217d3bbc Decision A: integration produit, base upstream master, pas de kernel GDN custom 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-24 12:54:28 +02:00
Richard Loyer 376b4a4a70 Angle revise: base upstream master (pas chraac), trou unique = prefill GDN Hexagon 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-24 12:52:08 +02:00
Richard Loyer cc5b033762 Engine cadrage: CLAUDE.md analyse R&D, verdict NPU-prefill/CPU-decode 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-24 12:34:14 +02:00