mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-06-24 16:49:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore(recon): bump pins to cuDNN-conv-capable engines (voice b6e4356, face 6107a24)

Browse Source 
Adds the opt-in cuDNN implicit-GEMM conv path (VOICEDETECT_GGML_CUDNN /
FACEDETECT_GGML_CUDNN, DEFAULT OFF -> zero build/runtime dep until enabled).
On GPU it kills the im2col-materialization bottleneck and reaches torch-cuDNN
parity on the spill-bound convs: SCRFD detect 14.8->6.4ms (2.3x, ~parity),
WeSpeaker ~parity, ERes2Net beats torch (1.10x); ArcFace/CAM++ neutral (no
spill). Parity exact (SCRFD <=1px, cosine=1.0). To USE it in LocalAI, the CUDA
backend build must enable the flag AND bundle libcudnn - deferred until a
cuDNN-bundled GPU image; flag stays OFF here.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
This commit is contained in:
Ettore Di Giacinto
2026-06-24 15:39:42 +00:00
parent 628b8a8e01
commit 9684c5dd7e
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
backend/go/face-detect/Makefile
View File

@@ -1,6 +1,6 @@
# face-detect backend Makefile.
#
# Upstream pin lives below as FACEDETECT_VERSION?=0a4799a... (.github/bump_deps.sh
# Upstream pin lives below as FACEDETECT_VERSION?=6107a24... (.github/bump_deps.sh
# can find and update it - matches the voice-detect / parakeet.cpp / whisper.cpp
# convention).
#
@@ -14,7 +14,7 @@
# The default target below does the proper clone-at-pin + cmake build so CI does
# not need a side-checkout.
FACEDETECT_VERSION?=0a4799a8a1febf666487e708160dba0c363d2af2
FACEDETECT_VERSION?=6107a2414fdaccc9ce8650b762f9436d20541cbe
FACEDETECT_REPO?=https://github.com/mudler/face-detect.cpp
GOCMD?=go

4
backend/go/voice-detect/Makefile
View File

@@ -1,6 +1,6 @@
# voice-detect backend Makefile.
#
# Upstream pin lives below as VOICEDETECT_VERSION?=45d2e6b... (.github/bump_deps.sh
# Upstream pin lives below as VOICEDETECT_VERSION?=b6e4356... (.github/bump_deps.sh
# can find and update it - matches the parakeet.cpp / whisper.cpp / ds4 convention).
#
# Local dev shortcut: if you already have an out-of-tree voice-detect.cpp build,
@@ -13,7 +13,7 @@
# The default target below does the proper clone-at-pin + cmake build so CI does
# not need a side-checkout.
VOICEDETECT_VERSION?=45d2e6b074bd4ca124e6ea2b39f9f549578e294f
VOICEDETECT_VERSION?=b6e43562aeed67fdfd0708d125b2088743b0852f
VOICEDETECT_REPO?=https://github.com/mudler/voice-detect.cpp
GOCMD?=go