8000 mpt : implement backwards compatiblity with duped output tensor by cebtenzzre · Pull Request #6139 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

mpt : implement backwards compatiblity with duped output tensor #6139

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

Merged
merged 3 commits into from
Mar 18, 2024
Merged

mpt : implement backwards compatiblity with duped output tensor #6139

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e2a4cac
mpt : implement backwards compatiblity with duped output tensor
cebtenzzre Mar 18, 2024
e5da60b
address review comment
cebtenzzre Mar 18, 2024
3f4b657
fix missing argument to create_tensor
cebtenzzre Mar 18, 2024
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
Prev Previous commit
fix missing argument to create_tensor
  • Loading branch information
@cebtenzzre
cebtenzzre committed Mar 18, 2024
commit 3f4b657a2751c33602ff867a98fea90e6e96ded7
4 changes: 2 additions & 2 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4302,7 +4302,7 @@ static bool llm_load_tensors(
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd});

model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false);
if (!model.output) {
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU
ml.n_created--; // artificial tensor
Expand Down Expand Up @@ -4508,7 +4508,7 @@ static bool llm_load_tensors(
model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, false);

model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false);
if (!model.output) {
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU
ml.n_created--; // artificial tensor
Expand Down
0