llama.cpp
69b74028 - ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.c

Commit
2 years ago
ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.c
Author
Parents
Loading