ROCmSoftwarePlatform
Upgrade ci to use ubuntu 24.04
Codecov Report
All modified and coverable lines are covered by tests :white_check_mark:
Additional details and impacted files
@@ Coverage Diff @@
## develop #3923 +/- ##
===========================================
- Coverage 92.41% 92.03% -0.38%
===========================================
Files 522 524 +2
Lines 22532 24077 +1545
===========================================
+ Hits 20822 22158 +1336
- Misses 1710 1919 +209
| Files with missing lines | Coverage Δ | |
|---|---|---|
| src/include/migraphx/instruction.hpp | 100.00% <ø> (ø) |
|
| src/include/migraphx/raw_data.hpp | 97.26% <100.00%> (-1.33%) |
:arrow_down: |
| src/include/migraphx/type_name.hpp | 100.00% <100.00%> (ø) |
|
| src/instruction.cpp | 88.14% <100.00%> (-0.75%) |
:arrow_down: |
:rocket: New features to boost your workflow:
- :snowflake: Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
![codecov[bot] avatar](https://avatars.githubusercontent.com/in/254?v=4 "Published by a pub.dev verified publisher"){kind=small}
| Test | Batch | Rate new 7869f8 |
Rate old fea22b |
Diff | Compare |
|---|---|---|---|---|---|
| torchvision-resnet50 | 64 | 3,251.21 | 3,224.68 | 0.82% | :white_check_mark: |
| torchvision-resnet50_fp16 | 64 | 6,902.70 | 6,871.66 | 0.45% | :white_check_mark: |
| torchvision-densenet121 | 32 | 2,444.02 | 2,433.28 | 0.44% | :white_check_mark: |
| torchvision-densenet121_fp16 | 32 | 4,224.15 | 4,210.30 | 0.33% | :white_check_mark: |
| torchvision-inceptionv3 | 32 | 1,623.09 | 1,614.36 | 0.54% | :white_check_mark: |
| torchvision-inceptionv3_fp16 | 32 | 2,712.35 | 2,696.30 | 0.60% | :white_check_mark: |
| cadene-inceptionv4 | 16 | 754.28 | 749.80 | 0.60% | :white_check_mark: |
| cadene-resnext64x4 | 16 | 814.81 | 810.05 | 0.59% | :white_check_mark: |
| slim-mobilenet | 64 | 6,691.76 | 6,653.72 | 0.57% | :white_check_mark: |
| slim-nasnetalarge | 64 | 197.45 | 196.50 | 0.48% | :white_check_mark: |
| slim-resnet50v2 | 64 | 3,447.89 | 3,436.85 | 0.32% | :white_check_mark: |
| bert-mrpc-onnx | 8 | 1,151.03 | 1,141.83 | 0.81% | :white_check_mark: |
| bert-mrpc-tf | 1 | 463.19 | 463.91 | -0.16% | :white_check_mark: |
| pytorch-examples-wlang-gru | 1 | 478.30 | 474.32 | 0.84% | :white_check_mark: |
| pytorch-examples-wlang-lstm | 1 | 435.20 | 466.24 | -6.66% | :red_circle: |
| torchvision-resnet50_1 | 1 | 812.09 | 810.37 | 0.21% | :white_check_mark: |
| cadene-dpn92_1 | 1 | 425.17 | 424.31 | 0.20% | :white_check_mark: |
| cadene-resnext101_1 | 1 | 394.10 | 392.70 | 0.36% | :white_check_mark: |
| onnx-taau-downsample | 1 | 398.43 | 396.47 | 0.49% | :white_check_mark: |
| dlrm-criteoterabyte | 1 | 31.94 | 31.82 | 0.37% | :white_check_mark: |
| dlrm-criteoterabyte_fp16 | 1 | 51.11 | 51.01 | 0.20% | :white_check_mark: |
| agentmodel | 1 | 8,604.37 | 8,756.49 | -1.74% | :white_check_mark: |
| unet_fp16 | 2 | 58.60 | 58.40 | 0.34% | :white_check_mark: |
| resnet50v1_fp16 | 1 | 1,071.16 | 1,075.67 | -0.42% | :white_check_mark: |
| resnet50v1_int8 | 1 | 878.28 | 891.37 | -1.47% | :white_check_mark: |
| bert_base_cased_fp16 | 64 | 1,169.92 | 1,161.69 | 0.71% | :white_check_mark: |
| bert_large_uncased_fp16 | 32 | 355.98 | 354.15 | 0.52% | :white_check_mark: |
| bert_large_fp16 | 1 | 195.23 | 193.72 | 0.78% | :white_check_mark: |
| distilgpt2_fp16 | 16 | 2,232.14 | 2,214.41 | 0.80% | :white_check_mark: |
| yolov5s | 1 | 515.86 | 514.41 | 0.28% | :white_check_mark: |
| tinyllama | 1 | 43.85 | 43.60 | 0.57% | :white_check_mark: |
| vicuna-fastchat | 1 | 44.23 | 43.94 | 0.67% | :white_check_mark: |
| whisper-tiny-encoder | 1 | 413.39 | 410.08 | 0.81% | :white_check_mark: |
| whisper-tiny-decoder | 1 | 413.06 | 410.36 | 0.66% | :white_check_mark: |
| llama2_7b | 1 | nan | nan | nan% | :x: |
| qwen1.5-7b | 1 | 23.55 | 23.45 | 0.45% | :white_check_mark: |
| phi3-3.8b | 1 | nan | nan | nan% | :x: |
| mask-rcnn | 1 | 18.61 | 18.47 | 0.77% | :white_check_mark: |
| llama3-8b | 1 | 21.75 | 21.18 | 2.69% | :white_check_mark: |
| whisper-large-encoder | 1 | 10.22 | 10.17 | 0.45% | :white_check_mark: |
| whisper-large-decoder | 1 | 97.70 | 98.10 | -0.41% | :white_check_mark: |
| mistral-7b | 1 | 23.76 | 23.65 | 0.48% | :white_check_mark: |
| FLUX.1-schnell | 1 | 896.68 | 908.97 | -1.35% | :white_check_mark: |
| nan | nan | nan | nan | nan% | :x: |
This build is not recommended to merge :red_circle:
:red_circle:bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output
:x:llama2_7b: ERROR - check error output
Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main
model = migraphx.parse_onnx(model_name, default_dim_value=batch)
RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed reading onnx file: /new-saved-models/llama2_7b/decoder_model.onnx:x:#qwen1.5-7b: ERROR - check error output
usage: accuracy_checker.py [-h] [--onnx ONNX] [--tf TF] [--provider PROVIDER]
[--batch BATCH] [--fill1] [--fill0] [--fp16]
[--argmax] [--verbose] [--tolerance TOLERANCE]
[--input-dim INPUT_DIM] [--target TARGET]
[--ort-run] [--ort-logging]
[--disable-offload-copy] [--disable-fast-math]
[--exhaustive_tune]
accuracy_checker.py: error: unrecognized arguments: input_ids attention_mask position_ids 1 256 @attention_mask 1 256 @position_ids 1 256:x:phi3-3.8b: ERROR - check error output
Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main
model = migraphx.parse_onnx(model_name, default_dim_value=batch)
RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed reading onnx file: /new-saved-models/phi3-3.8b/model.onnx:red_circle:mask-rcnn: FAILED: MIGraphX is not within tolerance - check verbose output
:x:#whisper-large-encoder: ERROR - check error output
Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main
model = migraphx.parse_onnx(model_name, default_dim_value=batch)
RuntimeError: /src/AMDMIGraphX/src/include/migraphx/op/convolution.hpp:100: normalize_compute_shape: CONVOLUTION: mismatched channel numbers