From cdb34a65f1616d5b8882122e1075700739a4fbd2 Mon Sep 17 00:00:00 2001 From: Richard Loyer Date: Mon, 25 May 2026 11:18:38 +0200 Subject: [PATCH] 0.32 = 1 thread + HTP residuel; fix t8+ngl0 = 14tok/s --- CLAUDE.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/CLAUDE.md b/CLAUDE.md index 537f84b..163be5f 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -111,3 +111,6 @@ Dev report: 4B/9B 6-13min/tour, jamais done. CAUSE: EngineLlmEngine generate() s ## #277 crash = stale .so + signature dist .so 09:40 = STATIC (0 libllama NEEDED) + ngl0 + 4s/tour OK. dev crash: (1) ancien .so shared dans jniLibs->ecraser; (2) generate=3args(sys,usr,maxTok), Kotlin doit appeler generate(h,sys,usr,64) pas (h,prompt,64). Tombstone libllama=stale. Fix dev: pull dist actuel + signature 2-arg sys/usr. + +## 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.