-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Checking high priority models #145
Comments
Yolov5The model passes, but I will leave the repro steps to get the onnx model:
|
Vicunavicuna-7b-v1.5 passes. Repro steps:
The same applies to vicuna-7b-v1.5-16k |
LLaMA-2 7BHuggingface Llama-2-7b-hf and Llama-2-7b-chat-hf are compiling, however the export fails similarly to vicuna |
Stable Diffusion 2.1Optimum command to get stable-diffusion-2-1:
|
WhisperOptimum command: |
GPT-J 6BOptimum command: |
Inception v3The model compiles with migraphx-driver. |
RetinaNetThe model compiles with migraphx-driver. |
MLSRWe checked two of the top trending SR models from huggingface A2N and AWSRN-BAM .Both are having 2, 3 and 4 scale versions. Results
The convolution details:
Which hits the offset limit: https://github.com/ROCmSoftwarePlatform/MIOpen/blob/develop/src/kernels/conv3x3.s#L463-L466 |
Did not see this error on my end. And I got both an encoder model and decoder model. |
Stable Diffusion 2.1These models fail with the latest develop on With reshape lazy enabled:
|
Ignore this, since it is a decoder, it will generate it one-by-one, make sense to use
The microsoft version fails with the following: migraphx-driver read 7B_float32/ONNX/LlamaV2_7B_float32.onnx --input-dim @x 1 2048 4096 @k_cache 1 32 2048 32 128 @v_cache 1 32 2048 32 128 @pos 1 @attn_mask 1 2048 2048
operator: Slice
/code/AMDMIGraphX/src/include/migraphx/check_shapes.hpp:157: only_dims: SLICE: inputs (starts, ends, and input_axes): Only 1d supported The onnxruntime converted version:
|
The text was updated successfully, but these errors were encountered: