[HW Accel Support]: AMD iGPU doesn't seem to work #20515
-
Describe the problem you are havingI'm using proxmox OS and running frigate inside a VM. I made the GPU passthrough and everything was working "fine" before the release of the 0.16.2 version. I'm trying to use the hwaccel through the iGPU of my ryzen 7 6800H but it doesn't seem to work anymore. I also tried using CPU as detector type but nothing changed Version0.16.2 Frigate config filemqtt:
enabled: true
host: mqtt
port: 1884
user: usr
password: pwd
go2rtc:
streams:
camera_balcone_record:
- ffmpeg:rtsp://192.168.178.68:554/h264#video=h264#hardware=vaapi
camera_balcone_detect:
- ffmpeg:http://192.168.178.68:8081#video=h264#hardware=vaapi
ffmpeg:
hwaccel_args: preset-vaapi # -> preset_intel-qsv-h265 per Intel
detectors:
onnx:
type: onnx # -> openvino per Intel
device: GPU
## Intel
# model:
# width: 300
# height: 300
# input_tensor: nhwc
# input_pixel_format: bgr
# path: /openvino-model/ssdlite_mobilenet_v2.xml
# labelmap_path: /openvino-model/coco_91cl_bkgr.txt
## AMD
model:
width: 320
height: 320
input_tensor: nchw
#input_pixel_format: bgr
input_dtype: float
model_type: yolo-generic
path: /config/yolov8n.onnx
labelmap_path: /labelmap/coco-80.txt
detect:
enabled: true # <---- disable detection until you have a working camera feed
width: 640
height: 480
fps: 5
record:
enabled: true
retain:
days: 0
alerts:
pre_capture: 10
post_capture: 10
retain:
days: 5
mode: motion
detections:
pre_capture: 10
post_capture: 10
retain:
days: 5
mode: motion
snapshots:
enabled: true
retain:
default: 30
quality: 80
objects:
track:
- person
- cat
- dog
- knife
- car
- bicycle
- motorcycle
cameras:
camera_balcone: # <------ Name the camera
enabled: true
ffmpeg:
inputs:
- path: rtsp://127.0.0.1:8554/camera_balcone_detect
roles:
- detect
- path: rtsp://127.0.0.1:8554/camera_balcone_record
roles:
- record
output_args:
record: preset-record-generic
review:
alerts:
required_zones:
- home_garden
detections:
required_zones:
- street
zones:
street:
coordinates: 0.257,0,1,0,1,0.725,0.753,0.483
objects:
- cat
- knife
- person
- motorcycle
- car
- bicycle
- dog
inertia: 3
loitering_time: 0
home_garden:
coordinates:
0,0,0.252,0,0.746,0.481,0.794,0.528,0.893,0.62,1,0.728,1,1,0.566,1,0.212,1,0,1,0,0.538,0,0.216
objects:
- cat
- knife
- person
inertia: 3
loitering_time: 0
version: 0.16-0
# telemetry:
# stats:
# intel_gpu_device: "drm:/dev/dri/card1"
semantic_search:
enabled: false
model_size: small
face_recognition:
enabled: false
model_size: small
lpr:
enabled: false
classification:
bird:
enabled: falsedocker-compose file or Docker CLI commandfrigate:
container_name: frigate
privileged: true # this may not be necessary for all setups
restart: unless-stopped
stop_grace_period: 30s # allow enough time to shut down the various services
image: ghcr.io/blakeblackshear/frigate:stable-rocm # Usare ghcr.io/blakeblackshear/frigate:stable per Intel
shm_size: "64mb" # update for your cameras based on calculation above
devices:
#- /dev/bus/usb:/dev/bus/usb # Passes the USB Coral, needs to be modified for other versions
#- /dev/apex_0:/dev/apex_0 # Passes a PCIe Coral, follow driver instructions here https://coral.ai/docs/m2/get-started/#2a-on-linux
#- /dev/video11:/dev/video11 # For Raspberry Pi 4B
#- /dev/dri/renderD128:/dev/dri/renderD128 # For intel hwaccel, needs to be updated for your hardware
- /dev/dri:/dev/dri # For VAAPI hwaccel, needs to be updated for your hardware -> SOLO PER AMD
- /dev/kfd:/dev/kfd # For AMD ROCm, needs to be updated for your hardware -> SOLO PER AMD
# group_add:
# - video
volumes:
- /etc/localtime:/etc/localtime:ro
- ./data/frigate/data/config:/config
- ./data/frigate/data/storage:/media/frigate
- type: tmpfs # Optional: 5GB of memory, reduces SSD/SD Card wear
target: /tmp/cache
tmpfs:
size: 5000000000
env_file:
- ./data/frigate/.env
cap_add:
- CAP_PERFMON
expose:
- 1984
ports:
- "5000:5000"
- "8554:8554"
- "8555:8555/tcp" # WebRTC over tcp
- "8555:8555/udp" # WebRTC over udp
networks:
home_net:
ipv4_address: 172.21.0.3
profiles: [all,home]Relevant Frigate log outputs6-rc: info: service s6rc-fdholder successfully stopped
s6-rc: info: service legacy-cont-init successfully stopped
s6-rc: info: service fix-attrs: stopping
s6-rc: info: service fix-attrs successfully stopped
s6-rc: info: service s6rc-oneshot-runner: stopping
s6-rc: info: service s6rc-oneshot-runner successfully stopped
s6-rc: info: service s6rc-fdholder: starting
s6-rc: info: service s6rc-oneshot-runner: starting
s6-rc: info: service s6rc-oneshot-runner successfully started
s6-rc: info: service fix-attrs: starting
s6-rc: info: service s6rc-fdholder successfully started
s6-rc: info: service fix-attrs successfully started
s6-rc: info: service legacy-cont-init: starting
s6-rc: info: service legacy-cont-init successfully started
s6-rc: info: service prepare: starting
s6-rc: info: service log-prepare: starting
s6-rc: info: service log-prepare successfully started
s6-rc: info: service nginx-log: starting
s6-rc: info: service go2rtc-log: starting
s6-rc: info: service frigate-log: starting
s6-rc: info: service certsync-log: starting
s6-rc: info: service go2rtc-log successfully started
s6-rc: info: service certsync-log successfully started
s6-rc: info: service nginx-log successfully started
s6-rc: info: service frigate-log successfully started
s6-rc: info: service prepare successfully started
s6-rc: info: service go2rtc: starting
s6-rc: info: service go2rtc successfully started
s6-rc: info: service go2rtc-healthcheck: starting
s6-rc: info: service frigate: starting
s6-rc: info: service frigate successfully started
s6-rc: info: service nginx: starting
s6-rc: info: service go2rtc-healthcheck successfully started
2025-10-15 23:44:49.276552301 [INFO] Starting NGINX...
2025-10-15 23:44:49.393892265 [INFO] Preparing Frigate...
2025-10-15 23:44:49.838770840 [INFO] Preparing new go2rtc config...
2025-10-15 23:44:49.925795845 [INFO] Starting Frigate...
2025-10-15 23:44:50.274409806 [INFO] Starting go2rtc...
2025-10-15 23:44:50.347813361 23:44:50.347 INF go2rtc platform=linux/amd64 revision=fa580c5 version=1.9.9
2025-10-15 23:44:50.347831241 23:44:50.347 INF config path=/dev/shm/go2rtc.yaml
2025-10-15 23:44:50.348338941 23:44:50.348 INF [rtsp] listen addr=:8554
2025-10-15 23:44:50.348616451 23:44:50.348 INF [api] listen addr=:1984
2025-10-15 23:44:50.349033211 23:44:50.348 INF [webrtc] listen addr=:8555
s6-rc: info: service nginx successfully started
s6-rc: info: service certsync: starting
s6-rc: info: service certsync successfully started
s6-rc: info: service legacy-services: starting
2025-10-15 23:44:50.868661342 [INFO] Starting certsync...
s6-rc: info: service legacy-services successfully started
2025-10-15 23:44:51.361058435 127.0.0.1 - - [15/Oct/2025:23:44:51 +0000] "" 400 0 "-" "-" "-"
2025-10-15 23:44:51.395681603 2025/10/15 23:44:51 [error] 202#202: *2 connect() failed (111: Connection refused) while connecting to upstream, client: 172.21.0.2, server: , request: "GET /api/stats HTTP/1.1", subrequest: "/auth", upstream: "http://127.0.0.1:5001/auth", host: "frigate:5000"
2025-10-15 23:44:51.395748973 2025/10/15 23:44:51 [error] 202#202: *2 auth request unexpected status: 502 while sending to client, client: 172.21.0.2, server: , request: "GET /api/stats HTTP/1.1", host: "frigate:5000"
2025-10-15 23:44:52.561795928 [2025-10-15 23:44:52] frigate.util.config INFO : Checking if frigate config needs migration...
2025-10-15 23:44:52.585281716 [2025-10-15 23:44:52] frigate.util.config INFO : frigate config does not need migration...
2025-10-15 23:44:52.649688923 [2025-10-15 23:44:52] frigate.app INFO : Starting Frigate (0.16.2-4d58206)
2025-10-15 23:44:52.661390842 [2025-10-15 23:44:52] peewee_migrate.logs INFO : Starting migrations
2025-10-15 23:44:52.664100412 [2025-10-15 23:44:52] peewee_migrate.logs INFO : There is nothing to migrate
2025-10-15 23:44:52.677077251 [2025-10-15 23:44:52] frigate.app INFO : Recording process started: 421
2025-10-15 23:44:52.689420231 [2025-10-15 23:44:52] frigate.app INFO : Review process started: 434
2025-10-15 23:44:52.695995270 [2025-10-15 23:44:52] frigate.app INFO : go2rtc process pid: 115
2025-10-15 23:44:52.717110799 [2025-10-15 23:44:52] detector.onnx INFO : Starting detection process: 446
2025-10-15 23:44:52.717416879 [2025-10-15 23:44:52] frigate.detectors.plugins.onnx INFO : ONNX: loaded onnxruntime module
2025-10-15 23:44:52.729033618 [2025-10-15 23:44:52] frigate.detectors.plugins.onnx INFO : ONNX: loading /config/yolov8n.onnx
2025-10-15 23:44:52.753109117 [2025-10-15 23:44:52] frigate.app INFO : Output process started: 472
2025-10-15 23:44:52.798515904 [2025-10-15 23:44:52] frigate.app INFO : Camera processor started for camera_balcone: 506
2025-10-15 23:44:52.832129563 [2025-10-15 23:44:52] frigate.app INFO : Capture process started for camera_balcone: 516
2025-10-15 23:44:52.976310965 terminate called after throwing an instance of 'onnxruntime::OnnxRuntimeException'
2025-10-15 23:44:52.976331025 what(): /onnxruntime/onnxruntime/core/providers/rocm/rocm_call.cc:124 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::RocmCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = hipError_t; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] /onnxruntime/onnxruntime/core/providers/rocm/rocm_call.cc:117 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::RocmCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = hipError_t; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] HIP failure 100: no ROCm-capable device is detected ; GPU=-1 ; hostname=e6b2eb18f2de ; file=/onnxruntime/onnxruntime/core/providers/rocm/rocm_common.h ; line=67 ; expr=hipGetDeviceProperties(&deviceProp, 0);
2025-10-15 23:44:52.976405934
2025-10-15 23:44:52.976423504
2025-10-15 23:44:52.976443344 Fatal Python error: Aborted
2025-10-15 23:44:52.976460184
2025-10-15 23:44:52.976530754 Current thread 0x0000783cc8fdd040 (most recent call first):
2025-10-15 23:44:52.976616064 File "/usr/local/lib/python3.11/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 537 in _create_inference_session
2025-10-15 23:44:52.976635364 File "/usr/local/lib/python3.11/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 465 in __init__
2025-10-15 23:44:52.976655164 File "/opt/frigate/frigate/detectors/plugins/onnx.py", line 53 in __init__
2025-10-15 23:44:52.976748424 File "/opt/frigate/frigate/detectors/__init__.py", line 18 in create_detector
2025-10-15 23:44:52.976768484 File "/opt/frigate/frigate/object_detection/base.py", line 57 in __init__
2025-10-15 23:44:52.976786694 File "/opt/frigate/frigate/object_detection/base.py", line 112 in run_detector
2025-10-15 23:44:52.976805184 File "/usr/lib/python3.11/multiprocessing/process.py", line 108 in run
2025-10-15 23:44:52.976823554 File "/opt/frigate/frigate/util/process.py", line 41 in run_wrapper
2025-10-15 23:44:52.976841564 File "/usr/lib/python3.11/multiprocessing/process.py", line 314 in _bootstrap
2025-10-15 23:44:52.976868954 File "/usr/lib/python3.11/multiprocessing/popen_fork.py", line 71 in _launch
2025-10-15 23:44:52.976888354 File "/usr/lib/python3.11/multiprocessing/popen_fork.py", line 19 in __init__
2025-10-15 23:44:52.976906184 File "/usr/lib/python3.11/multiprocessing/context.py", line 281 in _Popen
2025-10-15 23:44:52.976926134 File "/usr/lib/python3.11/multiprocessing/context.py", line 224 in _Popen
2025-10-15 23:44:52.976943724 File "/usr/lib/python3.11/multiprocessing/process.py", line 121 in start
2025-10-15 23:44:52.976962434 File "/opt/frigate/frigate/util/process.py", line 30 in start
2025-10-15 23:44:52.976979694 File "/opt/frigate/frigate/object_detection/base.py", line 195 in start_or_restart
2025-10-15 23:44:52.977018194 File "/opt/frigate/frigate/object_detection/base.py", line 163 in __init__
2025-10-15 23:44:52.977036594 File "/opt/frigate/frigate/app.py", line 391 in start_detectors
2025-10-15 23:44:52.977053454 File "/opt/frigate/frigate/app.py", line 648 in start
2025-10-15 23:44:52.977069344 File "/opt/frigate/frigate/__main__.py", line 104 in main
2025-10-15 23:44:52.977085554 File "/opt/frigate/frigate/__main__.py", line 108 in <module>
2025-10-15 23:44:52.977101804 File "<frozen runpy>", line 88 in _run_code
2025-10-15 23:44:52.977119344 File "<frozen runpy>", line 198 in _run_module_as_main
2025-10-15 23:44:52.977153364
2025-10-15 23:44:52.977958104 Extension modules: ruamel.yaml.clib._ruamel_yaml, _ruamel_yaml, psutil._psutil_linux, psutil._psutil_posix, pysqlite3._sqlite3, numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, _cffi_backend, charset_normalizer.md, requests.packages.charset_normalizer.md, requests.packages.chardet.md, PIL._imaging, markupsafe._speedups, regex._regex, setproctitle._setproctitle, zmq.backend.cython._zmq, rapidfuzz._feature_detector_cpp, rapidfuzz.distance._initialize_cpp, rapidfuzz.distance.metrics_cpp_avx2, rapidfuzz.fuzz_cpp_avx2, rapidfuzz.process_cpp_impl, rapidfuzz.utils_cpp, Levenshtein.levenshtein_cpp, pyclipper._pyclipper, shapely.lib, shapely._geos, shapely._geometry_helpers, scipy._lib._ccallback_c, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg.cython_lapack, scipy.linalg._cythonized_array_utils, scipy.linalg._solve_toeplitz, scipy.linalg._decomp_lu_cython, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg.cython_blas, scipy.linalg._matfuncs_expm, scipy.linalg._decomp_update, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.linalg._propack._spropack, scipy.sparse.linalg._propack._dpropack, scipy.sparse.linalg._propack._cpropack, scipy.sparse.linalg._propack._zpropack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, scipy.spatial._ckdtree, scipy._lib.messagestream, scipy.spatial._qhull, scipy.spatial._voronoi, scipy.spatial._distance_wrap, scipy.spatial._hausdorff, scipy.special._ufuncs_cxx, scipy.special._ufuncs, scipy.special._specfun, scipy.special._comb, scipy.special._ellip_harm_2, scipy.spatial.transform._rotation, scipy.optimize._group_columns, scipy.optimize._trlib._trlib, scipy.optimize._lbfgsb, _moduleTNC, scipy.optimize._moduleTNC, scipy.optimize._cobyla, scipy.optimize._slsqp, scipy.optimize._minpack, scipy.optimize._lsq.givens_elimination, scipy.optimize._zeros, scipy.optimize._highs.cython.src._highs_wrapper, scipy.optimize._highs._highs_wrapper, scipy.optimize._highs.cython.src._highs_constants, scipy.optimize._highs._highs_constants, scipy.linalg._interpolative, scipy.optimize._bglu_dense, scipy.optimize._lsap, scipy.optimize._direct, scipy.integrate._odepack, scipy.integrate._quadpack, scipy.integrate._vode, scipy.integrate._dop, scipy.integrate._lsoda, scipy.interpolate._fitpack, scipy.interpolate._dfitpack, scipy.interpolate._bspl, scipy.interpolate._ppoly, scipy.interpolate.interpnd, scipy.interpolate._rbfinterp_pythran, scipy.interpolate._rgi_cython, scipy.special.cython_special, scipy.stats._stats, scipy.stats._biasedurn, scipy.stats._levy_stable.levyst, scipy.stats._stats_pythran, scipy._lib._uarray._uarray, scipy.stats._ansari_swilk_statistics, scipy.stats._sobol, scipy.stats._qmc_cy, scipy.stats._mvn, scipy.stats._rcont.rcont, scipy.stats._unuran.unuran_wrapper, scipy.ndimage._nd_image, _ni_label, scipy.ndimage._ni_label, yaml._yaml, multidict._multidict, yarl._quoting_c, propcache._helpers_c, aiohttp._http_writer, aiohttp._http_parser, aiohttp._websocket.mask, aiohttp._websocket.reader_c, frozenlist._frozenlist, lxml._elementpath, lxml.etree, lxml.builder, ciso8601, pandas._libs.tslibs.ccalendar, pandas._libs.tslibs.np_datetime, pandas._libs.tslibs.dtypes, pandas._libs.tslibs.base, pandas._libs.tslibs.nattype, pandas._libs.tslibs.timezones, pandas._libs.tslibs.fields, pandas._libs.tslibs.timedeltas, pandas._libs.tslibs.tzconversion, pandas._libs.tslibs.timestamps, pandas._libs.properties, pandas._libs.tslibs.offsets, pandas._libs.tslibs.strptime, pandas._libs.tslibs.parsing, pandas._libs.tslibs.conversion, pandas._libs.tslibs.period, pandas._libs.tslibs.vectorized, pandas._libs.ops_dispatch, pandas._libs.missing, pandas._libs.hashtable, pandas._libs.algos, pandas._libs.interval, pandas._libs.lib, pandas._libs.ops, pandas._libs.hashing, pandas._libs.arrays, pandas._libs.tslib, pandas._libs.sparse, pandas._libs.internals, pandas._libs.indexing, pandas._libs.index, pandas._libs.writers, pandas._libs.join, pandas._libs.window.aggregations, pandas._libs.window.indexers, pandas._libs.reshape, pandas._libs.groupby, pandas._libs.json, pandas._libs.parsers, pandas._libs.testing (total: 175)
2025-10-15 23:44:52.983345724 [2025-10-15 23:44:52] frigate.api.fastapi_app INFO : Starting FastAPI app
2025-10-15 23:44:53.251760459 [2025-10-15 23:44:53] frigate.api.fastapi_app INFO : FastAPI startedRelevant go2rtc log outputI've only got the logs from portainer( Those that I pasted in the "Relevant Frigate log output")FFprobe output from your cameraffprobe http://192.168.178.68:8081
ffprobe version 2025-03-03-git-d21ed2298e-full_build-www.gyan.dev Copyright (c) 2007-2025 the FFmpeg developers
built with gcc 14.2.0 (Rev1, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-lcms2 --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-libdvdnav --enable-libdvdread --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-liblc3 --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 58.100 / 59. 58.100
libavcodec 61. 33.102 / 61. 33.102
libavformat 61. 9.107 / 61. 9.107
libavdevice 61. 4.100 / 61. 4.100
libavfilter 10. 9.100 / 10. 9.100
libswscale 8. 13.100 / 8. 13.100
libswresample 5. 4.100 / 5. 4.100
libpostproc 58. 4.100 / 58. 4.100
Input #0, mpjpeg, from 'http://192.168.178.68:8081':
Duration: N/A, bitrate: N/A
Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 640x480, 25 tbr, 25 tbnInstall methodProxmox via Docker Object DetectorOther Network connectionWireless Camera make and modelRaspberry Pi Zero2W with MotionEye OS Screenshots of the Frigate UI's System metrics pagesCannot reach the Web UI Any other information that may be helpfulRegarding the "network connection", the machine where frigate is running is connected through cable. The camera is connected to the wifi |
Beta Was this translation helpful? Give feedback.
Answered by
kRYstall9
Oct 17, 2025
Replies: 2 comments 11 replies
-
|
Based on your error logs, the issue is that your AMD iGPU is not being detected by the ROCm runtime. The error message "HIP failure 100: no ROCm-capable device is detected" indicates that ROCm cannot find a compatible AMD GPU(1). For AMD GPUs, you need to use the Docker Configuration: devices:
- /dev/dri:/dev/dri
- /dev/kfd:/dev/kfdAMD iGPU Support: Finding Your GPU Chipset: docker exec -it frigate /opt/rocm/bin/rocminfoTo find your AMD GPU chipset version, run(1): docker exec -it frigate /bin/bash -c '(unset HSA_OVERRIDE_GFX_VERSION && /opt/rocm/bin/rocminfo |grep gfx)'Setting the Override:
If your chipset isn't automatically detected, you'll need to set the services:
frigate:
environment:
HSA_OVERRIDE_GFX_VERSION: "10.0.0"Hardware Acceleration: environment:
LIBVA_DRIVER_NAME: radeonsiThe Model Limitations:
Try running the ROCm info commands first to see if your iGPU is detected, then configure the appropriate 📚 Sources: Have another question? Just tag @inkeep. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
Nothing changed in 0.16.2 that would affect this, but ROCm has been a work in progress from AMDs side, 0.17 had many improvements using the latest ROCm release |
Beta Was this translation helpful? Give feedback.
11 replies
-
|
I mean, if there's an alpha version of it, I could try and report back what I found out |
Beta Was this translation helpful? Give feedback.
-
|
Builds for every commit are listed in the sidebar You could use https://github.com/users/blakeblackshear/packages/container/frigate/545731020?tag=4e99ee0-rocm |
Beta Was this translation helpful? Give feedback.
-
|
Tried it out and this is what I'm getting know 
FRIGATE LOGSGO2RTC LOGSNGINX LOGSFRIGATE CONFIGFRIGATE ENVCommands |
Beta Was this translation helpful? Give feedback.
-
|
@NickM-27 Solved it by using an LXC container within Proxmox. It seems stable now, but I’ll let you know if anything weird happens along the way. |
Beta Was this translation helpful? Give feedback.
Answer selected by
NickM-27
-
|
Thanks for updating |
Beta Was this translation helpful? Give feedback.
-
How did you go about passing the amd igpu into the proxmox LXC? And what did the docker device section end up looking like? Thanks! |
Beta Was this translation helpful? Give feedback.
-
|
Hi @especially-relative, you could follow this guide. One thing to mention is that you should also add another device -> /dev/kfd So the hardware section of your lxc container should look like this: Regarding the docker device section, this is how mine looks like: PS: I'm using an "alpha" release of frigate because I was having some "GPU hang" errors |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@NickM-27 Solved it by using an LXC container within Proxmox. It seems stable now, but I’ll let you know if anything weird happens along the way.