Kazeia
/
Kazeia-engine
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Verdict: GDN HTP decode-only (2284), prefill GDN fallback CPU = ancre. B chiffre.

This commit is contained in:
Richard Loyer 2026-05-24 14:49:39 +02:00
parent eceacaba9a
commit 4dd863ecb5
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CLAUDE.md
View File

@ -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.