ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow quantization of ffn_gate_inp (#896)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-11-05 10:44:32 +02:00
committed by GitHub
parent 7978f04996
commit e68f50be9a
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

@@ -455,6 +455,7 @@ 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