diff --git a/CLAUDE.md b/CLAUDE.md index fc8ea39..897c3e6 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -66,3 +66,6 @@ GATED_DELTA_NET ABSENT du profil HTP = GDN 100% CPU confirme. HTP top: CONT(copi ## Note: gen lente cli = decode sur HTP (pas le fix) -dev HTP0 garde decode sur NPU = 3-4 t/s + reasoning 200tok = 0.6 t/s percu. Vrai: prefill HTP 58 / decode CPU 13 (-dev none). cli mono-device, ne splitte pas. Cible = JNI prefill HTP -> bascule decode CPU. 0.6 t/s = artefact bench, pas perf. + +## Mesure split reference (Qwen3.5-4B-Q4_0, GDN-HTP fixe) +prefill HTP=55.5 / decode CPU=15.3 t/s. ~512tok prefill 9s + 64tok 4s = 13s reponse. cli lent=mono-device; JNI bascule prefill HTP->decode CPU. B-2 etape1 bit-correct livre.