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

Correctif: OPFILTER inexistant, isolation GDN_cpu = bench DEBUG; bugs+qualite requalifies

This commit is contained in:
Richard Loyer 2026-05-24 15:58:18 +02:00
parent d05483b13a
commit 627f9a80e2
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

@ -52,3 +52,6 @@ HTP pp512=45/pp1024=45 plat: partie batchable saturee des pp128 (ne prouve PAS l
## Bug cli localise (24/05) ## 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. 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.
## Correctif methode (24/05)
GGML_HEXAGON_OPFILTER N EXISTE PAS (invente). OPMASK=phase (SKIP_QUANTIZE/COMPUTE/QUEUE) global, pas par-op. GDN_KERNEL=0 = decode only. => pas d isolation GDN_cpu sans rebuild. Voie propre: bench rebuild DEBUG -> profiler total+Reste_htp meme run, GDN_cpu=total-Reste_htp (thermals neutres). Bug1 unaccounted 2^44 = underflow size_t buffer HTP >1 ubatch, fix borne, a lever pour pp512 RAG. Bug2 llama_params_fit abort -dev none = 3e chemin CPU casse, upstream, hors A/B. Qualite: PRE-validee 1 run reasoning, protocole FR a faire.