Skip to content

llama : fix non-quantization of expert gating tensors #5754

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 1 commit into from
Feb 28, 2024
Merged

llama : fix non-quantization of expert gating tensors #5754

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11213,7 +11213,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
quantize &= !params->only_copy;

// do not quantize expert gating tensors
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_FFN_GATE_INP, "weight");
// NOTE: can't use LLM_TN here because the layer number is not known
quantize &= name.find("ffn_gate_inp.weight") == std::string::npos;

// do not quantize positional embeddings and token types (BERT)
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD, "weight");
Expand Down