ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-03 10:30:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow quantization of ffn_gate_inp

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-11-04 11:34:10 +02:00
parent cd8d0b0832
commit 04e57f4356
4 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -454,6 +454,7 @@ extern "C" {
enum ggml_type ffn_gate_type; // feedforward network gate type
enum ggml_type ffn_down_type; // feedforward network down type
enum ggml_type ffn_up_type; // feedforward network up type
enum ggml_type ffn_gate_inp_type; // routed experts probabilities typy (relevant for MoE models only)
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored