8000 MPT : clone wte to output at load time by cebtenzzre · Pull Request #3626 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

MPT : clone wte to output at load time #3626

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.

Sign up for GitHub

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

Closed
wants to merge 2 commits into from
Closed

MPT : clone wte to output at load time #3626

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b577e63
MPT : fix an offload func typo
cebtenzzre Oct 14, 2023
4207444
MPT : clone wte to output at load time
cebtenzzre Oct 14, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
MPT : fix an offload func typo
  • Loading branch information
@cebtenzzre
cebtenzzre committed Oct 14, 2023
commit b577e6374ed6bd8a670cbb731adf563522aa9538
2 changes: 1 addition & 1 deletion llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5532,7 +5532,7 @@ static struct ggml_cgraph * llm_build_mpt(
wsize * n_embd_head,
wsize * n_embd_head * (n_head + 2 * n_head_kv),
wsize * n_embd_head * (n_head + n_head_kv));
offload_func_kq(Kcur);
offload_func_v(tmpv);

ggml_set_name(Qcur, "Qcur");
ggml_set_name(Kcur, "Kcur");
Expand Down
0