tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: remove mistaken fallback macro

Browse Source 
fallback logic was already implemented but i was too sleepy to realise

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-06-25 01:31:53 +08:00
parent a02b360f2c
commit 1b23fec005
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cpu/simd-mappings.h
View File

@ -135,10 +135,6 @@
uint16x8_t v_h = vec_convert_to_fp16(v_hd, 0);
return vec_extract(v_h, 0);
}
#else
// fallback to the generic implementation
#define GGML_CPU_FP16_TO_FP32(x) GGML_FP16_TO_FP32(x)
#define GGML_CPU_FP32_TO_FP16(x) GGML_FP32_TO_FP16(x)
#endif
// On ARM NEON, it's quicker to directly convert x -> x instead of calling into ggml_lookup_fp16_to_fp32,