Final: pte 4B 15/2.2GB > GGUF 0.32; merge=t8 mais pte reste mieux 4B; gguf utile=gros modeles

This commit is contained in:
Richard Loyer 2026-05-25 12:21:04 +02:00
parent cdb34a65f1
commit 7aae1f5fc7
1 changed files with 3 additions and 0 deletions

View File

@ -114,3 +114,6 @@ dist .so 09:40 = STATIC (0 libllama NEEDED) + ngl0 + 4s/tour OK. dev crash: (1)
## 0.32 cause: threads=1 + HTP residuel
CPU ngl0: t1=1.6, t8=14tok/s. in-app 0.32<1.6 = 1 thread + HTP init residuel. FIX dev: cp.n_threads=8 (verifie pas bride Android) + ne PAS init hexagon (ngl0 mais lib charge htp). Speaker 4B CPU pur t8=14=4s/tour. cap64. Confirmer log n_threads/ngl au load. signature 2-arg+static deja OK.
## Comparatif final 4B in-app (dev)
pte NPU: 15tok/s, 1.7s, 2.2GB. GGUF bridge: 0.32tok/s (1thread+HTP res), 4.5GB. GGUF standalone t8: 13. pte~standalone match, 2x moins RAM. #277 merge-able SI bridge t8 (->13~pte) mais RAM reste 2x. SEUL gain GGUF = 9B/modeles sans pte. 4B: pte gagne. Bloque sur: n_threads=8 + couper HTP init in-app.