Commit Graph

3 Commits

Author SHA1 Message Date
Richard Loyer a7c0e96793 RAPPORT §7: piste kernel GDN fermee — GDN-compute != goulot prefill (fork ql)
A/B pp512 mesure: serial f32=89.5 (vrai baseline) = fp16 89.65 = WY chunkwise 89.6.
3 schemas calcul GDN (0.5x/1x/2.5x flops) -> pp512 plat => l'arithmetique GDN ne
limite pas le prefill sur le fork ql (GDN-HTP). Mur ailleurs (denses/FFN/attn/op-batch).
Corrige premisse "GDN=ancre" (ancien tree GDN-CPU) et le baseline fantome "98".
Aucune optim kernel GDN (chunkwise/HMX/fp16) ne bouge le prefill.

ql -> 50e250d: fp16 serial validate (oracle 28/28, env KZ_F16 defaut OFF), WY chunkwise
conserve inutilise, HMX-per-tete NO-GO. Pousser pp512 = profiler ops non-GDN HTP.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 21:46:05 +02:00
Richard Loyer b2fc564f04 Engine sur fork qualcomm: decode dense 15.5>pte, 3.5 ~11, KVq8+t4+fa+lm_head-Q4; prefill 93/285; RAG cross 24-28k
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 15:53:14 +02:00
Richard Loyer 1252f32bd3 Rapport R&D complet: synthese session, perf, cascade, #277, briques, reste a faire
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 22:27:34 +02:00