administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-05-07 05:55:27 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

ROCm Optimizations (#23118)

Browse Source 
* Update to ROCm 7.2.3

* Add inference time for 9060XT

* Update times

* Update hardware info for latest ROCm

* Add env vars to save kernels and miopen database

* re-enable face recognition for ROCm

* Update

* Save LLVM cache
This commit is contained in:
Nicolas Mowen 2026-05-05 15:33:43 -06:00 committed by GitHub
parent 52a3301726
commit 76a1230885
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 18 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docker/rocm/Dockerfile
View File

@ -13,7 +13,7 @@ ARG ROCM
RUN apt update -qq && \ RUN apt update -qq && \
apt install -y wget gpg && \ apt install -y wget gpg && \
wget -O rocm.deb https://repo.radeon.com/amdgpu-install/7.2/ubuntu/jammy/amdgpu-install_7.2.70200-1_all.deb && \ wget -O rocm.deb https://repo.radeon.com/amdgpu-install/7.2.3/ubuntu/jammy/amdgpu-install_7.2.3.70203-1_all.deb && \
apt install -y ./rocm.deb && \ apt install -y ./rocm.deb && \
apt update && \ apt update && \
apt install -qq -y rocm apt install -qq -y rocm
@ -78,6 +78,10 @@ ENV MIGRAPHX_DISABLE_MIOPEN_FUSION=1
ENV MIGRAPHX_DISABLE_SCHEDULE_PASS=1 ENV MIGRAPHX_DISABLE_SCHEDULE_PASS=1
ENV MIGRAPHX_DISABLE_REDUCE_FUSION=1 ENV MIGRAPHX_DISABLE_REDUCE_FUSION=1
ENV MIGRAPHX_ENABLE_HIPRTC_WORKAROUNDS=1 ENV MIGRAPHX_ENABLE_HIPRTC_WORKAROUNDS=1
ENV MIOPEN_CUSTOM_CACHE_DIR=/config/model_cache/migraphx
ENV MIOPEN_USER_DB_PATH=/config/model_cache/migraphx
ENV AMD_COMGR_CACHE=1
ENV AMD_COMGR_CACHE_DIR=/config/model_cache/migraphx
COPY --from=rocm-dist / / COPY --from=rocm-dist / /

2
docker/rocm/requirements-wheels-rocm.txt
View File

@ -1 +1 @@
onnxruntime-migraphx @ https://github.com/NickM-27/frigate-onnxruntime-rocm/releases/download/v7.2.0/onnxruntime_migraphx-1.23.1-cp311-cp311-linux_x86_64.whl onnxruntime-migraphx @ https://github.com/NickM-27/frigate-onnxruntime-rocm/releases/download/v7.2.3-1/onnxruntime_migraphx-1.24.4-cp311-cp311-linux_x86_64.whl

2
docker/rocm/rocm.hcl
View File

@ -1,5 +1,5 @@
variable "ROCM" { variable "ROCM" {
default = "7.2.0" default = "7.2.3"
} }
variable "HSA_OVERRIDE_GFX_VERSION" { variable "HSA_OVERRIDE_GFX_VERSION" {
default = "" default = ""

4
docs/docs/configuration/object_detectors.md
View File

@ -1023,9 +1023,9 @@ detectors:
### ONNX Supported Models ### ONNX Supported Models
| Model | Nvidia GPU | AMD GPU | Notes | | Model | Nvidia GPU | AMD GPU | Notes |
| ----------------------------- | ---------- | ------- | --------------------------------------------------- | | ------------------------------------ | ---------- | ------- | --------------------------------------------------- |
| [YOLOv9](#yolo-v3-v4-v7-v9-2) | ✅ | ✅ | Supports CUDA Graphs for optimal Nvidia performance | | [YOLOv9](#yolo-v3-v4-v7-v9-2) | ✅ | ✅ | Supports CUDA Graphs for optimal Nvidia performance |
| [RF-DETR](#rf-detr) | ✅ | ❌ | Supports CUDA Graphs for optimal Nvidia performance | | [RF-DETR](#rf-detr) | ✅ | ⚠️ | Supports CUDA Graphs for optimal Nvidia performance |
| [YOLO-NAS](#yolo-nas-1) | ⚠️ | ⚠️ | Not supported by CUDA Graphs | | [YOLO-NAS](#yolo-nas-1) | ⚠️ | ⚠️ | Not supported by CUDA Graphs |
| [YOLOX](#yolox-1) | ✅ | ✅ | Supports CUDA Graphs for optimal Nvidia performance | | [YOLOX](#yolox-1) | ✅ | ✅ | Supports CUDA Graphs for optimal Nvidia performance |
| [D-FINE / DEIMv2](#d-fine--deimv2-1) | ⚠️ | ❌ | Not supported by CUDA Graphs | | [D-FINE / DEIMv2](#d-fine--deimv2-1) | ⚠️ | ❌ | Not supported by CUDA Graphs |

9
docs/docs/frigate/hardware.md
View File

@ -223,10 +223,11 @@ Apple Silicon can not run within a container, so a ZMQ proxy is utilized to comm
With the [ROCm](../configuration/object_detectors.md#amdrocm-gpu-detector) detector Frigate can take advantage of many discrete AMD GPUs. With the [ROCm](../configuration/object_detectors.md#amdrocm-gpu-detector) detector Frigate can take advantage of many discrete AMD GPUs.
| Name | YOLOv9 Inference Time | YOLO-NAS Inference Time | | Name | YOLOv9 Inference Time | YOLO-NAS Inference Time | RF-DETR Inference Time |
| --------- | --------------------------- | ------------------------- | | -------------- | --------------------------- | ------------------------- | ---------------------- |
| AMD 780M | t-320: ~ 14 ms s-320: 20 ms | 320: ~ 25 ms 640: ~ 50 ms | | AMD 780M | t-320: ~ 14 ms s-320: 20 ms | 320: ~ 25 ms 640: ~ 50 ms | |
| AMD 8700G | | 320: ~ 20 ms 640: ~ 40 ms | | AMD 8700G | | 320: ~ 20 ms 640: ~ 40 ms | |
| AMD 9060XT 16G | t-320: ~ 4 ms s-320: 5 ms | 320: ~ 6 ms | Nano-320: ~ 90 ms |
## Community Supported Detectors ## Community Supported Detectors

1
frigate/detectors/detection_runners.py
View File

@ -132,7 +132,6 @@ class ONNXModelRunner(BaseModelRunner):
return model_type in [ return model_type in [
EnrichmentModelTypeEnum.paddleocr.value, EnrichmentModelTypeEnum.paddleocr.value,
EnrichmentModelTypeEnum.jina_v2.value, EnrichmentModelTypeEnum.jina_v2.value,
EnrichmentModelTypeEnum.arcface.value,
ModelTypeEnum.rfdetr.value, ModelTypeEnum.rfdetr.value,
ModelTypeEnum.dfine.value, ModelTypeEnum.dfine.value,
] ]