llama: update to commit de4c07f93 (#10655)

0cefd46f · Jeffrey Morgan · GitHub · ad035ad5 · 0cefd46f · 0cefd46f
Unverified Commit 0cefd46f authored May 12, 2025 by Jeffrey Morgan Committed by GitHub May 12, 2025
20 changed files
--- a/ml/backend/ggml/ggml/src/ggml-cuda/getrows.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/getrows.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/mmq.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/mmq.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/mmvq.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/mmvq.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/quantize.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/quantize.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/sum.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/sum.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu