-
Notifications
You must be signed in to change notification settings - Fork 806
Add support SA8797(also used by SA8397) #16695
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16695
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 21 PendingAs of commit bba3ce5 with merge base 4c8132c ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
Hello @ares89 do you intend to merge to |
I want to merge to |
a9ee422 to
da23496
Compare
|
@kirklandsign |
|
cc: @cccclai @shewu-quic @chunit-quic @haowhsu-quic @winskuo-quic since this is a QNN backend related update! |
cccclai
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you! Looks good to me, will wait to see if qcom folks have more feedback
|
Hmm somehow the CI is not triggered. Can I get some help to land this PR? @SS-JIA @Gasoonjia @JacobSzwejbka |
This PR needs a
|
Tried update branch and seems working |
|
@ares89 the lint runner is failing, can you fix the error? |
fixed ^_^ |
Summary
Fixes #16535
feat(backends/qualcomm): add support for SA8797/SA8397 chipset and V81 architecture
Test plan
I have tested the changes by compiling and running a model on the SA8397 with QNN SDK v2.42.0.251225
python examples/qualcomm/oss_scripts/llama/llama.py -b build-android -m SA8797 --temperature 0 --model_mode hybrid --max_seq_len 1024 --prefill_ar_len 128 --decoder_model qwen3-0_6b --compile_only --prompt "what is 1+1" --checkpoint /home/xxx/.cache/meta_checkpoints/Qwen_Qwen3-0.6B.pth --artifact ./llama_qnn/qwen3/8797_04python examples/qualcomm/oss_scripts/llama/llama.py -b build-android -m SA8797 -s localhost:5555 --decoder_model qwen3-0_6b --model_mode hybrid --prefill_ar_len 128 --max_seq_len 1024 --prompt "what is 1+1" --pre_gen_pte D:\\tmp\\llama_qnn_qwen3_06b\\8797_04