ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)

Browse source 
* ggml: dynamic x86_64 feature detection for FP32 <-> FP16/BF16 conversion

* move fp converter to ggml-cpu

* Switch ggml_compute_forward_get_rows_f16/bf16 to new ggml_cpu_fp16/bf16_to_fp32
This commit is contained in:
SXX 2025-04-26 22:05:31 +08:00 • committed by GitHub
parent d5fe4e81bd
commit 77d5e9a76a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 101 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml/include/ggml-cpu.h
View file

@ -133,6 +133,11 @@ extern "C" {
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_cpu_reg(void);
GGML_BACKEND_API void ggml_cpu_fp32_to_fp16(const float *, ggml_fp16_t *, int64_t);
GGML_BACKEND_API void ggml_cpu_fp16_to_fp32(const ggml_fp16_t *, float *, int64_t);
GGML_BACKEND_API void ggml_cpu_fp32_to_bf16(const float *, ggml_bf16_t *, int64_t);
GGML_BACKEND_API void ggml_cpu_bf16_to_fp32(const ggml_bf16_t *, float *, int64_t);
#ifdef __cplusplus
}
#endif