Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp

src/llama-grammar.cpp

@@ -2,7 +2,7 @@
 
 #include "llama-impl.h"
 #include "llama-vocab.h"
-#include "llama-sampling.h"
+#include "llama-sampler.h"
 
 #include <cmath>
 #include <algorithm>

src/llama-sampler.cpp

@@ -1,4 +1,4 @@
-#include "llama-sampling.h"
+#include "llama-sampler.h"
 
 #include "llama-impl.h"
 #include "llama-vocab.h"

src/llama-sampler.h

@@ -1,7 +1,5 @@
 #pragma once
 
-// TODO: rename llama-sampling.h/.cpp to llama-sampler.h/.cpp ?
-
 #include "llama.h"
 
 #include <vector>

src/llama.cpp

@@ -10,7 +10,7 @@ static bool old_mixtral_warning_showed = false;
 #include "llama-batch.cpp"
 #include "llama-vocab.cpp"
 #include "llama-grammar.cpp"
-#include "llama-sampling.cpp"
+#include "llama-sampler.cpp"
 #include "llama-kv-cache.cpp"
 #include "llama-kv-cache-iswa.cpp"
 #include "llama-memory-hybrid.cpp"