tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 12:55:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: fix wrong refactor of ggml-base

Browse Source 
ref: https://github.com/ggml-org/llama.cpp/pull/14317#discussion_r2164176555

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-06-24 22:56:05 +08:00
parent e4a7f84d37
commit 1e6ebb2b1b
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-impl.h
View File

@ -390,6 +390,9 @@ static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) {
#define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x) #define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
#define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x) #define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x)
#define GGML_FP16_TO_FP32(x) GGML_COMPUTE_FP16_TO_FP32(x)
#define GGML_FP32_TO_FP16(x) GGML_COMPUTE_FP32_TO_FP16(x)
// precomputed f32 table for f16 (256 KB) // precomputed f32 table for f16 (256 KB)
// defined in ggml.c, initialized in ggml_init() // defined in ggml.c, initialized in ggml_init()
GGML_API float ggml_table_f32_f16[1 << 16]; GGML_API float ggml_table_f32_f16[1 << 16];

1
ggml/src/ggml-quants.c
View File

@ -4,7 +4,6 @@
#include "ggml-quants.h" #include "ggml-quants.h"
#include "ggml-impl.h" #include "ggml-impl.h"
#include "ggml-cpu/ggml-cpu-impl.h" #include "ggml-cpu/ggml-cpu-impl.h"
#include "ggml-cpu/simd-mappings.h"
#include "ggml-cpu.h" #include "ggml-cpu.h"
#include <math.h> #include <math.h>