Skip to content
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

Migrating HL compile and export to infer APIs #214

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

asmigosw
Copy link
Contributor

@asmigosw asmigosw commented Jan 8, 2025

Migrating HL compile API and export API to infer APIs

quic-swatia and others added 3 commits January 7, 2025 12:05
[QEff. Finetune] : Plotting the correct (scaled) loss on tensorboard for the training.
Removing this change for now: Plotting the loss for each sample of eval rather the average

Signed-off-by: Swati Allabadi <[email protected]>
Co-authored-by: Swati Allabadi <[email protected]>
quic#187)

* QNN Compilation support in QEFFAutoModelForCausalLM High Level APIs

	1. Modified qnn_compiler.py to include qnn_binary_dir path to support hash suffix in qpc directory name.
	2. Added tests/qnn_tests/test_causal_lm_models_qnn.py for unit testing.
	3. Modified qnn_config.json to enable compiler_enable_depth_first if qnn_config file is passed.
	4. Added _qnn_compile function in QEFFBaseModel to support QNN Compilation.

Signed-off-by: Shubham Agrawal <[email protected]>

* Increased Non-CLI Non-QAIC Tests timeout

Signed-off-by: Rishin Raj <[email protected]>

* Added sudo for executing QNN Docker commands

Signed-off-by: Rishin Raj <[email protected]>

---------

Signed-off-by: Shubham Agrawal <[email protected]>
Signed-off-by: Rishin Raj <[email protected]>
Co-authored-by: Rishin Raj <[email protected]>
Change-Id: If27fbc1636ed1fe9b475d07cef7c83ed7dc46ca8
Signed-off-by: Asmita Goswami <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants