cuda : fix rope + add tests (llama/7452)

* cuda : fix rope pos data

ggml-ci

* ggml : drop mode & 1 == 1 support for ggml_rope

ggml-ci

* ggml : support freq_factors for f16 rope (CPU)

ggml-ci

* tests : add rope tests using frequency factors

ggml-ci
This commit is contained in:
Georgi Gerganov
2024-06-16 18:19:48 +03:00
parent c9dcb75118
commit c4d6958b3e
3 changed files with 21 additions and 5 deletions
+2 -2
View File
@@ -283,9 +283,9 @@ void ggml_cuda_op_rope(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const bool is_neox = mode & 2;
const bool is_glm = mode & 4;
if (is_neox) {
pos = (const int32_t *) src1_d;
pos = (const int32_t *) src1_d;
if (is_neox) {
if (src2 != nullptr) {
freq_factors = (const float *) src2->data;
}