-
Notifications
You must be signed in to change notification settings - Fork 51
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
base: main
Are you sure you want to change the base?
Onboarding Qwen3moe #406
Conversation
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]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Signed-off-by: Dipankar Sarkar <[email protected]>
Minor Changes 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]>
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. |
Onboarding Qwen3Moe