Richard Loyer
|
f638bdbd94
|
GDN chunkwise P1.1: chunk C=64 refactor neutre, oracle 28/28+pp98 OK, squelette pret pour intra-chunk batch
|
2026-05-26 16:15:55 +02:00 |
|
Richard Loyer
|
837d9de766
|
GDN chunkwise: doc P1 math+structure+gate (refactor chunks C=64 phase1)
|
2026-05-26 16:13:34 +02:00 |
|
Richard Loyer
|
aa363e652f
|
GDN chunkwise P0: oracle test-backend-ops 28/28 HTP0 (gate régression), baseline pp512=93, boucle build live; P1 chunk-f32 en cours
|
2026-05-26 16:04:58 +02:00 |
|
Richard Loyer
|
de9543de2a
|
Chantier4 GDN chunkwise: plan grounded metrics, kernel pp_thread sériel localisé, HMX core_dot_chunk_fp16 réutilisable, build htp-v79 incrémental OK
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-26 15:55:25 +02:00 |
|
Richard Loyer
|
8c793a22b5
|
FIX GDN prefill HTP: GQA broadcast h%heads, charabia resolu, pp512 58 t/s (+16%)
|
2026-05-24 17:57:20 +02:00 |
|
Richard Loyer
|
31afd64eec
|
GDN dump: FARF hors logcat (sink dedie req), lib nettoyee, B-2 tracke. Produit 50/13 pret
|
2026-05-24 17:42:34 +02:00 |
|
Richard Loyer
|
6e63110f8a
|
GDN prefill: bug=handoff multi-token (pas GQA), fix=dump bisection; defaut CPU sur
|
2026-05-24 17:38:35 +02:00 |
|
Richard Loyer
|
33e848be3c
|
Chantier 3: gate GDN-prefill leve = charabia, +11% INVALIDE, defaut CPU. Honnete: kernel a fixer
|
2026-05-24 17:22:52 +02:00 |
|
Richard Loyer
|
b82420fd46
|
Chantier 3 etape 1: GDN prefill HTP, gate leve, pp512 +11% (50->55)
|
2026-05-24 17:20:09 +02:00 |
|
Richard Loyer
|
ae842df5ae
|
Chantier 2 clos: CONT low-ROI (opsync gonfle, reshape structurel) -> 3 prioritaire
|
2026-05-24 17:17:24 +02:00 |
|
Richard Loyer
|
024f3b8ed6
|
Chantier 1 clos: prefill pp2048 sain (46t/s), hang=cli only hors JNI
|
2026-05-24 17:16:44 +02:00 |