llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)

d7d7e996 · Jeffrey Morgan · GitHub · 2db96c18 · d7d7e996 · d7d7e996
Unverified Commit d7d7e996 authored Feb 26, 2025 by Jeffrey Morgan Committed by GitHub Feb 26, 2025
20 changed files
--- a/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
--- a/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-impl.h
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-impl.h
--- a/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-quants.c
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu-quants.c
--- a/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu.c
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu.c
--- a/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu.cpp
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/ggml-cpu.cpp
--- a/ml/backend/ggml/ggml/src/ggml-cpu/llamafile/sgemm.cpp
+++ b/ml/backend/ggml/ggml/src/ggml-cpu/llamafile/sgemm.cpp
--- a/ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt
--- a/ml/backend/ggml/ggml/src/ggml-cuda/binbcast.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/binbcast.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/common.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/common.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/concat.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/concat.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/convert.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/convert.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/cp-async.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/cp-async.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/cpy.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/cpy.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/cross-entropy-loss.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/cross-entropy-loss.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-common.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-common.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-mma-f16.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-mma-f16.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-tile-f16.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-tile-f16.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-tile-f32.cu
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-tile-f32.cu
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-vec-f16.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-vec-f16.cuh
--- a/ml/backend/ggml/ggml/src/ggml-cuda/fattn-vec-f32.cuh
+++ b/ml/backend/ggml/ggml/src/ggml-cuda/fattn-vec-f32.cuh