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

[NPU] Llama2 prefill use ov sdp #12310

Merged
merged 7 commits into from
Nov 1, 2024
Merged

Conversation

cyita
Copy link
Contributor

@cyita cyita commented Oct 31, 2024

Description

Llama2 prefill use ov sdp. Qwen performance drop, disabled.

1. Why the change?

2. User API changes

3. Summary of the change

4. How to test?

  • N/A
  • Unit test: Please manually trigger the PR Validation here by inputting the PR number (e.g., 1234). And paste your action link here once it has been successfully finished.
  • Application test
  • Document test
  • ...

5. New dependencies

  • New Python dependencies
    - Dependency1
    - Dependency2
    - ...
  • New Java/Scala dependencies and their license
    - Dependency1 and license1
    - Dependency2 and license2
    - ...

@cyita cyita requested a review from rnwang04 November 1, 2024 01:22
@@ -200,8 +200,14 @@ def attention(self,

query_states = self.transpose(query_states, [0, 2, 1, 3])
key_states = self.transpose(key_states, [0, 2, 1, 3])
use_ov_sdp = (mode == "prefill") and use_prefill_sdp
print(f"-------------------- use_ov_sdp: {use_ov_sdp}, groupsize: {self.group_size}")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove this print ?

Copy link
Contributor

@rnwang04 rnwang04 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

others LGTM.

@cyita cyita merged commit 05c5d02 into intel-analytics:main Nov 1, 2024
1 check passed
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.

2 participants