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

cuda : fix build

Browse source
This commit is contained in:
Georgi Gerganov 2024-03-27 10:31:52 +02:00
parent 013721df2b
commit 6be02b5969
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 44 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml-cuda/fattn.cuh
View file

@ -1,6 +1,3 @@
#include "common.cuh"
void ggml_cuda_flash_attn_ext(
ggml_backend_cuda_context & ctx,
const ggml_tensor * Q, const ggml_tensor * K, const ggml_tensor * V,
const ggml_tensor * mask, ggml_tensor * KQV);
void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst);