Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-10-29 22:20:15 +01:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix FA Q src index (1 -> 0) (#9374)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-09-08 22:01:02 +03:00 committed by GitHub
parent 3f7ccfd649
commit e079bffb66
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/fattn.cu
View File

@ -152,7 +152,7 @@ static void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, g
} \
static void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_tensor * Q = dst->src[1];
ggml_tensor * Q = dst->src[0];
ggml_tensor * K = dst->src[1];
ggml_tensor * V = dst->src[2];
@ -227,7 +227,7 @@ static void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, gg
} \
static void ggml_cuda_flash_attn_ext_vec_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_tensor * Q = dst->src[1];
ggml_tensor * Q = dst->src[0];
ggml_tensor * K = dst->src[1];
ggml_tensor * V = dst->src[2];