Kazeia
/
Kazeia-engine
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
59 Commits 1 Branch 0 Tags 217 MiB
Shell 100%
Go to file
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
.claude Rapport R&D complet: synthese session, perf, cascade, #277, briques, reste a faire 2026-05-25 22:27:34 +02:00
dist 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 2026-05-26 15:53:14 +02:00
docs GDN chunkwise P1.2: VTCM state prefill=neutre, prouve compute-bound 3S2/tok -> gain=WY matmul (palier dur). oracle 28/28, pp98 2026-05-26 16:30:08 +02:00
ql@50e250d7bc RAPPORT §7: piste kernel GDN fermee — GDN-compute != goulot prefill (fork ql) 2026-05-26 21:46:05 +02:00
.gitignore 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 2026-05-26 15:53:14 +02:00
CLAUDE.md R&D: battre pte=lm_head HMX INT4+spec decode+ctx binary; mur=lm_head CPU 2026-05-25 18:46:28 +02:00
RAPPORT_RD.md RAPPORT §7: piste kernel GDN fermee — GDN-compute != goulot prefill (fork ql) 2026-05-26 21:46:05 +02:00
c4.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
casc.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
casc2.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
casc3.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
cascade_test.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
cf.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
qcmp.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00
spk.sh Dist Kazeia-Engine: libs arm64+headers+JNI bridge+INTEGRATION/TTS doc; STT reste ORT 2026-05-24 21:55:01 +02:00