GPU failing to enable (Win 11, docker)

[kaffo]

Hey folks, I'm having trouble running on my GPU and I suspect something is setup incorrectly.
I'm on Windows 11 and I can run nvidia-smi fine in the container
However running the docker image I'm not getting the expected output on startup, I'm seeing a warning others have seen but I've not seen a resolution to

docker run -p 8080:8080 -v D:/models:/models -e DEBUG=true --gpus all --name local-ai -ti localai/localai:latest-gpu-nvidia-cuda-12 --models-path /models --threads 12
@@@@@
Skipping rebuild
@@@@@
If you are experiencing issues with the pre-compiled builds, try setting REBUILD=true
If you are still experiencing issues with the build, try setting CMAKE_ARGS and disable the instructions set as needed:
CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF"
see the documentation at: https://localai.io/basics/build/index.html
Note: See also https://github.com/go-skynet/LocalAI/issues/288
@@@@@
CPU info:
model name      : 12th Gen Intel(R) Core(TM) i7-12700KF
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid pni pclmulqdq vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves avx_vnni umip waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize flush_l1d arch_capabilities
CPU:    AVX    found OK
CPU:    AVX2   found OK
CPU: no AVX512 found
@@@@@
5:38PM INF env file found, loading environment variables from file envFile=.env
5:38PM DBG Setting logging to debug
5:38PM INF Starting LocalAI using 12 threads, with models path: /models
5:38PM INF LocalAI version: v2.24.0 (87b7648591573ea59c090b1095ba3073623933ad)
5:38PM DBG CPU capabilities: [3dnowprefetch abm adx aes apic arch_capabilities avx avx2 avx_vnni bmi1 bmi2 clflush clflushopt clwb cmov constant_tsc cpuid cx16 cx8 de ept ept_ad erms f16c flush_l1d fma fpu fsgsbase fsrm fxsr gfni ht hypervisor ibpb ibrs ibrs_enhanced invpcid invpcid_single lahf_lm lm mca mce md_clear mmx movbe movdir64b movdiri msr mtrr nonstop_tsc nopl nx pae pat pcid pclmulqdq pdpe1gb pge pni popcnt pse pse36 rdpid rdrand rdseed rdtscp rep_good sep serialize sha_ni smap smep ss ssbd sse sse2 sse4_1 sse4_2 ssse3 stibp syscall tpr_shadow tsc tsc_adjust tsc_deadline_timer tsc_reliable umip vaes vme vmx vnmi vpclmulqdq vpid waitpkg x2apic xgetbv1 xsave xsavec xsaveopt xsaves xtopology]
WARNING: failed to determine nodes: open /sys/devices/system/node: no such file or directory
WARNING: failed to read int from file: open /sys/class/drm/card0/device/numa_node: no such file or directory
WARNING: failed to determine nodes: open /sys/devices/system/node: no such file or directory
WARNING: error parsing the pci address "vgem"
5:38PM DBG GPU count: 1
5:38PM DBG GPU: card #0 @vgem

this is from running

docker run -p 8080:8080 -v D:/models:/models -e DEBUG=true --gpus all --name local-ai -ti localai/localai:latest-gpu-nvidia-cuda-12 --models-path /models --threads 12

Some output from inside the container

# ls /sys/class/drm/card0/device 
driver_override  drm  modalias  subsystem  uevent
ls /sys/devices/system
clockevents  clocksource  container  cpu  memory

Any suggestions to try?