diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /tests/test-quantize-fns.cpp | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'tests/test-quantize-fns.cpp')
| -rw-r--r-- | tests/test-quantize-fns.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/test-quantize-fns.cpp b/tests/test-quantize-fns.cpp index cf4664b3..638b921b 100644 --- a/tests/test-quantize-fns.cpp +++ b/tests/test-quantize-fns.cpp @@ -69,7 +69,7 @@ static float reference_quantization_error(ggml_type_traits_t & qfns, size_t test qfns.from_float(test_data, tmp_q.data(), test_size); qfns.to_float(tmp_q.data(), tmp_out.data(), test_size); - qfns.from_float_reference(test_data, tmp_q.data(), test_size); + qfns.from_float_ref(test_data, tmp_q.data(), test_size); qfns.to_float(tmp_q.data(), tmp_out_ref.data(), test_size); return array_rmse(tmp_out.data(), tmp_out_ref.data(), test_size); @@ -92,7 +92,7 @@ static float dot_product_error( auto vdot = ggml_internal_get_type_traits(qfns.vec_dot_type); - qfns.from_float_reference(test_data1, tmp_q1.data(), test_size); + qfns.from_float_ref(test_data1, tmp_q1.data(), test_size); vdot.from_float(test_data2, tmp_q2.data(), test_size); float result = INFINITY; |