Kazeia-engine/dist/lib
Richard Loyer 224b375a10 chantier dense-HMX: avancement — ni magnitude, ni NaN, ni shape pure (value/context-spécifique)
3 hypothèses éliminées par mesure: overflow fp16 (act=9.8), NaN/Inf inputs (0), shape pure (isolation
synthétique k=4096 ne crashe pas). Op fautive = o_proj MUL_MAT q4_0 k=4096 après FLASH_ATTN_EXT.
Prochaines étapes révisées (dump-and-replay value-vs-context, instrumentation DSP log-vers-buffer).
OPLOG mis à jour (nan/inf) dans dist/lib. ql -> commit OPLOG.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 14:09:52 +02:00
..
libc++_shared.so 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
libggml-base.so 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
libggml-cpu.so 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
libggml-hexagon.so chantier dense-HMX: avancement — ni magnitude, ni NaN, ni shape pure (value/context-spécifique) 2026-05-27 14:09:52 +02:00
libggml-htp-v68.so 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
libggml-htp-v69.so 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
libggml-htp-v73.so 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
libggml-htp-v75.so 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
libggml-htp-v79.so 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
libggml-htp-v81.so 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
libggml.so 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
libkazeia_engine.so dist: ROOT CAUSE crash dense-HTP = matmul HMX (fp16) ; fix = HVX pour le dense 2026-05-27 12:42:15 +02:00
libllama-common.so 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
libllama.so 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