Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml-cpu: fuse RMS_NORM + MUL on CPU backend (#22423)

Browse Source
This commit is contained in:
zzzzwc
2026-05-06 15:41:14 +08:00
committed by GitHub
parent 07eaf919ed
commit f08f20a0e3
3 changed files with 115 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/ops.h
+1
View File
@@ -44,6 +44,7 @@ void ggml_compute_forward_concat(const struct ggml_compute_params * params, stru
void ggml_compute_forward_silu_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
void ggml_compute_forward_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
void ggml_compute_forward_rms_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
void ggml_compute_forward_rms_norm_mul_fused(const struct ggml_compute_params * params, struct ggml_tensor * dst_rms_norm, struct ggml_tensor * dst_mul);
void ggml_compute_forward_rms_norm_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
void ggml_compute_forward_group_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
void ggml_compute_forward_l2_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);