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

Bug cli = overflow buffer HTP gros prefill (2^44), pas init; qualite 4B OK

This commit is contained in:
Richard Loyer 2026-05-24 15:52:33 +02:00
parent 753d8be2b0
commit d05483b13a
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

@ -49,3 +49,6 @@ prefill pp32/128/512: CPU 18.5/18.7/18.7 (PLAT), HTP 18.5/44/47. HTP ×2.5 reel
## pp1024 + bornes GDN (24/05) ## pp1024 + bornes GDN (24/05)
HTP pp512=45/pp1024=45 plat: partie batchable saturee des pp128 (ne prouve PAS la taille du GDN). CPU 18.7=53.5ms/tok modele entier (PAS GDN isole). HTP 22.2ms = GDN_cpu+R_htp, donc GDN_cpu<22.2 borne haute. Recompense B-2 entre ~62 et ~160 t/s selon GDN_cpu non mesure. Profiler HTP (GGML_HEXAGON_PROFILE+OPSYNC) inerte: cli pend AU prefill, bench masque DEBUG. Mesurer GDN_cpu = prerequis avant engager kernel; debloquer cli ouvre le profiler. Existence B chiffree, recompense NON. HTP pp512=45/pp1024=45 plat: partie batchable saturee des pp128 (ne prouve PAS la taille du GDN). CPU 18.7=53.5ms/tok modele entier (PAS GDN isole). HTP 22.2ms = GDN_cpu+R_htp, donc GDN_cpu<22.2 borne haute. Recompense B-2 entre ~62 et ~160 t/s selon GDN_cpu non mesure. Profiler HTP (GGML_HEXAGON_PROFILE+OPSYNC) inerte: cli pend AU prefill, bench masque DEBUG. Mesurer GDN_cpu = prerequis avant engager kernel; debloquer cli ouvre le profiler. Existence B chiffree, recompense NON.
## Bug cli localise (24/05)
cli prompt court -ngl99 HTP: REPOND, FR coherent (4B-Q4_0 qualite OK). Hang seulement gros prefill: HTP unaccounted=17592186042685 (2^44, underflow size_t buffer) = bug multi-ubatch, PAS init/handoff. CPU -dev none court: abort llama_params_fit (2e bug distinct). bench OK car 1 ubatch. Qualite franchie -> B-2 garde sens. Reste: GDN_cpu via bench rebuild DEBUG.