Ettore Di Giacinto c4df41d209 chore(recon): bump pins to small-spatial + stem conv kernels (voice 99b1804, face 47fdab6) ...

Measured-gap-driven conv kernels: small-spatial (fill the register tile when
output width <= tile width) + small-IC stem + strided-1x1/downsample recovery.
ArcFace recognizer 0.57 -> 0.70x MLAS @1t (the closest conv model), WeSpeaker
0.65 -> 0.79x @1t. Parity cosine=1.0 / detect <=1px. The OC-block-sharing lever
was a measured dead-end (deep stride-1 is L3-weight-bandwidth bound, not
read-port bound) and was NOT shipped. Kernel ceiling reached; further gap needs
an algorithm-class change (cache-blocked weight-stationary GEMM, or q8 weights).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

2026-06-23 23:44:04 +00:00

..

.gitignore

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

gofacedetect_test.go

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

gofacedetect.go

feat(recon): honor LocalAI per-model threads in voice/face-detect backends

2026-06-22 13:32:02 +00:00

main.go

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

Makefile

chore(recon): bump pins to small-spatial + stem conv kernels (voice 99b1804, face 47fdab6)

2026-06-23 23:44:04 +00:00

options.go

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

package.sh

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

run.sh

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00

test.sh

feat(face-detect): add purego Go backend for face-detect.cpp

2026-06-22 00:26:15 +00:00