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-double-float.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-double-float.cpp')
| -rw-r--r-- | tests/test-double-float.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/test-double-float.cpp b/tests/test-double-float.cpp index 753dae91..6aac4737 100644 --- a/tests/test-double-float.cpp +++ b/tests/test-double-float.cpp @@ -14,7 +14,7 @@ #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wdouble-promotion" -// ggml.c::quantize_row_q4_0_reference +// ggml.c::quantize_row_q4_0_ref inline static uint8_t round_orig(float v0) { return ((int8_t) (round(v0))) + 8; } // ggml.c::ggml_silu_f32 @@ -24,7 +24,7 @@ inline static float silu_orig(float x) { #pragma GCC diagnostic pop -// ggml.c::quantize_row_q4_0_reference +// ggml.c::quantize_row_q4_0_ref inline static uint8_t round_float(float v0) { return (int8_t)roundf(v0) + 8; } // ggml.c::ggml_silu_f32 |