-
Notifications
You must be signed in to change notification settings - Fork 451
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
support turbomind head_dim 64 #2715
Conversation
@@ -241,10 +241,10 @@ void invokeProcessKV_v2(char** blocks, | |||
int block = WARPS * WARP_SIZE; | |||
dim3 grid((max_q_len + CTA_S - 1) / CTA_S, head_num, batch_size); | |||
|
|||
auto invoke = [&](auto tkv) { | |||
auto invoke = [&](auto tkv, const auto dim) { |
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.
@lzhangzz what does tkv
mean?
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.
I think it means target kv datatype
@zhulinJulia24 may add the following models into tm test set
|
done
done |
* support head_dim 64 * fix unit-test * fix wrong dispatch * fix comments * fix comments
Motivation
support models with head_dim = 64 like
InternVL/InternVL2-1B/
andQwen/Qwen1.5-0.5B-Chat/