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

GDN chunkwise: HMX fp16 bloque bit-exact, HVX qf32 3-5sem; reste 55/15 CPU exact

This commit is contained in:
Richard Loyer 2026-05-24 22:12:47 +02:00
parent 1a6637bd67
commit 9675280760
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

@ -102,3 +102,6 @@ BUG=enable_thinking default true -> /no_think ignore -> ramble anglais. FIX: --r
## TTS statut 24/05
Talker=qwen3 GGUF chargeable engine (poids OK). Decoder RTF0.96 chraac valide histo. MAIS audio bout-en-bout sur engine NON valide: bench standalone segfault/libomp perm; vrai TTS=JNI Talker->codes->CP->decoder (integration app). GDN chunkwise: agent en cours. Optim sure: release Thinker -2.5GB, KV f16.
## GDN chunkwise verdict
Chunkwise batchable, 55->100 credible MAIS HMX accumulateur FP16 -> bit-exact impossible. Voie=HVX qf32 3-5sem frontiere. Prefill GDN-HTP encore not-bit-correct (2287 default OFF), decode CPU bit-exact. Reco: rester 55/15, gain pas worth (4s masques). Optim sure=release Thinker+KV f16.