ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA FA WIP - it now works for Q8_0 + Q8_0 for KV cache

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-03-03 19:02:13 +02:00
parent 0a6542b503
commit 47474c1c7e
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -3275,6 +3275,10 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
if (op->src[0]->ne[0] == 128) {
return true;
}
if (op->src[1]->ne[0] == 192 && op->src[2]->ne[0] == 128) {
return (op->src[1]->type == GGML_TYPE_F16 && op->src[2]->type == GGML_TYPE_F16) ||
(op->src[1]->type == GGML_TYPE_Q8_0 && op->src[2]->type == GGML_TYPE_Q8_0);
}
if (op->src[0]->ne[0] == 64 && op->src[1]->type == GGML_TYPE_F16) {
return true;
}