cuda : get_row_rounding F32 (ggerganov#4095)

* Fix ggerganov#4017 * Update ggml-cuda.cu Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update ggml-cuda.cu Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> --------- Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Sanctum-AI · Nov 23, 2023 · 11649d4 · 11649d4
1 parent 2abce2c
commit 11649d4
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/ggml-cuda.cu b/ggml-cuda.cu
@@ -6356,6 +6356,7 @@ static int64_t get_row_rounding(ggml_type type) {
         case GGML_TYPE_Q8_0:
             return max_compute_capability >= CC_RDNA2 ? 128 : 64;
         case GGML_TYPE_F16:
+        case GGML_TYPE_F32:
             return 1;
         case GGML_TYPE_Q2_K:
             return max_compute_capability >= CC_RDNA2 ? 128 : 32;
@@ -6378,6 +6379,7 @@ static int64_t get_row_rounding(ggml_type type) {
         case GGML_TYPE_Q8_0:
             return 64;
         case GGML_TYPE_F16:
+        case GGML_TYPE_F32:
             return 1;
         case GGML_TYPE_Q2_K:
         case GGML_TYPE_Q3_K: