Skip to content

Onboarding Qwen3moe #406

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

Open
wants to merge 25 commits into
base: main
Choose a base branch
from
Open

Onboarding Qwen3moe #406

wants to merge 25 commits into from

Conversation

qcdipankar
Copy link
Contributor

@qcdipankar qcdipankar commented May 15, 2025

Onboarding Qwen3Moe

Screenshot 2025-08-04 135021

@qcdipankar qcdipankar self-assigned this May 15, 2025
@qcdipankar qcdipankar marked this pull request as draft May 15, 2025 17:22
@quic quic locked as off-topic and limited conversation to collaborators May 15, 2025
@quic quic unlocked this conversation May 16, 2025
@qcdipankar qcdipankar requested a review from vbaddi May 16, 2025 10:49
@qcdipankar qcdipankar marked this pull request as ready for review May 21, 2025 09:22
@qcdipankar qcdipankar requested a review from quic-hemagnih as a code owner May 21, 2025 09:22
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
qcdipankar and others added 3 commits August 4, 2025 07:48
@qcdipankar qcdipankar changed the title Qwen3moe Onboarding Qwen3moe Aug 5, 2025
qcdipankar and others added 4 commits August 8, 2025 13:54
@qcdipankar qcdipankar marked this pull request as draft August 13, 2025 00:36
@qcdipankar qcdipankar added in-review Review process is ongoing wip Work in progress labels Aug 13, 2025
@qcdipankar qcdipankar marked this pull request as ready for review August 23, 2025 07:16
@qcdipankar
Copy link
Contributor Author

Currently The PR is ready and tested for merge after the address of all the comments from @vbaddi and @quic-rishinr. The PR is still not merged primarily because the compilation time for full layer is taking more than 30 hrs but output has been verified for 1,2 and full layers. The compilation issue has been reported to compiler team with 2-layer time passes log. Currently @vbaddi has asked for a new approach to moe block and if that can reduce the compilation time else we will go with this approach and merge it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
1.21.0 in-review Review process is ongoing model-enablement wip Work in progress
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants