ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 10:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Slightly better matrix x vector on Zen4/AVX2 for iq2_k_r4, iq3_k_r4, iq4_k_r4 (#148)

Browse Source 
* Slightly better matrix x vector on Zen4/AVX2 for iq2_k_r4, iq3_k_r4, iq4_k_r4

More importantly: simplify.

* Minor

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-17 18:55:38 +01:00
committed by GitHub
parent a648191c2c
commit 2247afa967
2 changed files with 55 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/llama-bench/llama-bench.cpp
View File

@@ -238,7 +238,7 @@ struct cmd_params {
int reps;
bool verbose;
bool warmup;
bool repack;
bool repack = false;
output_formats output_format;
output_formats output_format_stderr;
};
@@ -632,7 +632,7 @@ struct cmd_params_instance {
std::vector<float> tensor_split;
bool use_mmap;
bool embeddings;
bool repack;
bool repack = false;
llama_model_params to_llama_mparams() const {
llama_model_params mparams = llama_model_default_params();
@@ -811,7 +811,7 @@ struct test {
std::vector<float> tensor_split;
bool use_mmap;
bool embeddings;
bool repack;
bool repack = false;
int n_prompt;
int n_gen;
std::string test_time;