llama: update vendored code to commit 40c6d79f (#7875)

527cc978 · Jeffrey Morgan · GitHub · a37f4a86 · 527cc978 · 527cc978
Unverified Commit 527cc978 authored Dec 10, 2024 by Jeffrey Morgan Committed by GitHub Dec 10, 2024
20 changed files
--- a/llama/ggml-cuda/vendors/cuda.h
+++ b/llama/ggml-cuda/vendors/cuda.h
--- a/llama/ggml-cuda/vendors/hip.h
+++ b/llama/ggml-cuda/vendors/hip.h
--- a/llama/ggml-cuda/vendors/musa.h
+++ b/llama/ggml-cuda/vendors/musa.h
--- a/llama/ggml-cuda/rwkv-wkv.cu
+++ b/llama/ggml-cuda/rwkv-wkv.cu
--- a/llama/ggml-cuda/rwkv-wkv.cuh
+++ b/llama/ggml-cuda/rwkv-wkv.cuh
--- a/llama/ggml-impl.h
+++ b/llama/ggml-impl.h
--- a/llama/ggml-metal-embed.metal
+++ b/llama/ggml-metal-embed.metal
--- a/llama/ggml-metal-embed_darwin_arm64.s
+++ b/llama/ggml-metal-embed_darwin_arm64.s
--- a/llama/ggml-metal-impl.h
+++ b/llama/ggml-metal-impl.h
--- a/llama/ggml-metal.h
+++ b/llama/ggml-metal.h
--- a/llama/ggml-metal.metal
+++ b/llama/ggml-metal.metal
--- a/llama/ggml-metal_darwin_arm64.m
+++ b/llama/ggml-metal_darwin_arm64.m
--- a/llama/ggml-quants.c
+++ b/llama/ggml-quants.c
--- a/llama/ggml-quants.h
+++ b/llama/ggml-quants.h
--- a/llama/ggml-threading.cpp
+++ b/llama/ggml-threading.cpp
--- a/llama/ggml-threading.h
+++ b/llama/ggml-threading.h
--- a/llama/ggml.c
+++ b/llama/ggml.c
--- a/llama/ggml.h
+++ b/llama/ggml.h
--- a/llama/json-schema-to-grammar.cpp
+++ b/llama/json-schema-to-grammar.cpp
--- a/llama/json-schema-to-grammar.h
+++ b/llama/json-schema-to-grammar.h