vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.cpp

Browse source
This commit is contained in:
John 2024-01-17 00:03:58 +01:00 • committed by GitHub
parent 196348de53
commit 80350daeda
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama.cpp
View file

@ -3438,7 +3438,8 @@ static bool llm_load_tensors(
if (gguf_find_tensor(ml.ctx_gguf, tn(LLM_TENSOR_OUTPUT, "weight").c_str()) >= 0) {
model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab});
} else {
model.output = model.tok_embd;
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_tensors++; // artificial tensor
}
}