Verdict: GDN HTP decode-only (2284), prefill GDN fallback CPU = ancre. B chiffre.
This commit is contained in:
parent
eceacaba9a
commit
4dd863ecb5
|
|
@ -43,3 +43,6 @@ GGUF/llama.cpp archivés vers `/opt/Kazeia/to_delete`. Git local: commits régul
|
||||||
|
|
||||||
## Mesures 24/05 (build f0fe1058b, Pad3, Q4_0)
|
## 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.
|
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.
|
||||||
|
|
||||||
|
## Verdict 24/05 (mesure honnête, pp égal)
|
||||||
|
prefill pp32/128/512: CPU 18.5/18.7/18.7 (PLAT), HTP 18.5/44/47. HTP ×2.5 reel a pp512. GDN HTP = decode-only (ggml-hexagon.cpp:2284 "n_tokens!=1 -> CPU fallback"). Prefill GDN sur CPU serie = ancre. Kernel GDN-prefill chunked HTP = le sujet B, gros gain (FA/FFN HTP pourraient ~159). cli boucle = bug runtime aval, PAS compile (bench=meme graphe). Decode tranche, prefill = chantier.
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue