From eceacaba9a040f43906bdaee7ecec96c68944089 Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Sun, 24 May 2026 14:33:17 +0200
Subject: [PATCH] Mesures 4B: HTP prefill 44 / CPU decode 13.4, qwen35_compile
 HTP fonctionne

---
 CLAUDE.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CLAUDE.md b/CLAUDE.md
index 172b964..d357a5b 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -40,3 +40,6 @@ Source: `/opt/Kazeia/to_delete/llama.cpp` = upstream ggerganov + ggml-hexagon +
 ## Limite assistant
 R&D LLM frontière (kernels HVX bit-exacts, quant) = aide partielle, je le dis au cas par cas.
 GGUF/llama.cpp archivés vers `/opt/Kazeia/to_delete`. Git local: commits réguliers. — Richard & Damien.
+
+## Mesures 24/05 (build f0fe1058b, Pad3, Q4_0)
+prefill HTP pp128=44 / decode CPU tg16=13.4 ; HTP decode=4.4, CPU prefill pp32=18.5. → split prefill-HTP/decode-CPU OK, qwen35_compile HTP fonctionne. cli boucle (76min/0tok) — bench OK. Cible: pousser prefill 44→. Staging tablette: /data/local/tmp/kz-engine.