administrator/frigate - frigate - Gitea: Git with a cup of tea

administrator/frigate

mirror of https://github.com/blakeblackshear/frigate.git synced 2026-10-07 23:32:48 +03:00

Author	SHA1	Message	Date
Nicolas MowenandGitHub	9e74adf812	Guard against memory allocation in graph capture (#24192 ) CI / AMD64 Build (push) Canceled after 0s Details CI / ARM Build (push) Canceled after 0s Details CI / Jetson Jetpack 6 (push) Canceled after 0s Details CI / AMD64 Extra Build (push) Canceled after 0s Details CI / ARM Extra Build (push) Canceled after 0s Details CI / Synaptics Build (push) Canceled after 0s Details CI / Assemble and push default build (push) Canceled after 0s Details	2026-09-04 09:13:30 -06:00
Josh HawkinsandGitHub	41bc24cce4	use extended graph optimization for jinav2 (#24079 ) CI / AMD64 Build (push) Canceled after 0s Details CI / ARM Build (push) Canceled after 0s Details CI / Jetson Jetpack 6 (push) Canceled after 0s Details CI / AMD64 Extra Build (push) Canceled after 0s Details CI / ARM Extra Build (push) Canceled after 0s Details CI / Synaptics Build (push) Canceled after 0s Details CI / Assemble and push default build (push) Canceled after 0s Details The CUDA execution provider returns an identical vector for every image when jina-clip-v2 is built below ORT_ENABLE_EXTENDED, so every thumbnail embedding written on a GPU was the same normalized garbage and semantic search returned the same results for any query. Reproduced on two different NVIDIA cards, across onnxruntime 1.22 and 1.24, and on both the 0.17 and 0.18 CUDA stacks, so it isn't specific to any of those. ORT_ENABLE_ALL isn't an option because it fails to build on CPU with a SimplifiedLayerNormFusion error, leaving EXTENDED as the only level that works on both providers. jinav1 is unaffected and stays on BASIC.	2026-08-24 09:13:16 -05:00