From 17a78f1c6ab77953cd693a24463e41e5e10290c3 Mon Sep 17 00:00:00 2001 From: Richard Loyer Date: Sun, 24 May 2026 16:53:08 +0200 Subject: [PATCH] Profil: GDN absent HTP (100% CPU confirme), CONT+SSM_CONV+MULMAT dominent; lib restauree --- CLAUDE.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/CLAUDE.md b/CLAUDE.md index 6dae1bf..54f3eca 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -58,3 +58,6 @@ GGML_HEXAGON_OPFILTER N EXISTE PAS (invente). OPMASK=phase (SKIP_QUANTIZE/COMPUT ## Optim prefill Qwen3.5-4B (24/05) Sweep ngl: 0=18.7/8=19/16=18/24=23/32=33/99=45 -> monotone, full offload gagne. Sweep t/b @ngl99: t8+b512=49.9 (best,+11%), t6=46.6, t4=41. CPU threads portent GDN-CPU+ amorti b512. OPTIMUM prefill = ngl99/t8/b512=49.9. decode reste CPU. Pas de compromis partiel. Plafond 50 = GDN-CPU; lever B-2 pour >. + +## Profil HTP prefill (24/05) +GATED_DELTA_NET ABSENT du profil HTP = GDN 100% CPU confirme. HTP top: CONT(copies) 4.6s, SSM_CONV 2.9, MUL_MAT 2.9, REPEAT, CPY. opsync gonfle, GDN_cpu = residu sale (~total-Reste), facteur 2.5 non leve net. Fait dur: 24/32 couches GDN hors NPU = sujet B-2. CONT/copies = overhead a tailler aussi. prefill 48.9.