diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-17 18:55:38 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-17 18:55:38 +0100 |
| commit | 9b6d14a2991da41af4aa7ef64a712c63b73ad9fe (patch) | |
| tree | c98c2aa75a9877bf7b6485452bfea0347823b46c /examples | |
| parent | 514ae086200a8cfd78af6a71b6c6ee14931ddc0e (diff) | |
Slightly better matrix x vector on Zen4/AVX2 for iq2_k_r4, iq3_k_r4, iq4_k_r4 (#148)
* 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>
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/llama-bench/llama-bench.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 7741a227..75fe40d1 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -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; |