llama: update vendor code to commit ba1cb19c (#8101)

llama/patches/0011-relative-include-paths.patch

@@ -4,27 +4,13 @@ Date: Tue, 3 Dec 2024 21:30:51 -0800
 Subject: [PATCH] relative include paths
 
 ---
- ggml/src/ggml-cpu/ggml-cpu-aarch64.c | 2 +-
- ggml/src/ggml-cpu/ggml-cpu.c         | 2 +-
- ggml/src/ggml-cpu/ggml-cpu.cpp       | 2 +-
- ggml/src/ggml-quants.c               | 2 +-
- 4 files changed, 4 insertions(+), 4 deletions(-)
+ ggml/src/ggml-cpu/ggml-cpu.c   | 2 +-
+ ggml/src/ggml-cpu/ggml-cpu.cpp | 3 +--
+ ggml/src/ggml-quants.c         | 2 +-
+ 3 files changed, 3 insertions(+), 4 deletions(-)
 
-diff --git a/ggml/src/ggml-cpu/ggml-cpu-aarch64.c b/ggml/src/ggml-cpu/ggml-cpu-aarch64.c
-index 11152385..bbf8934e 100644
---- a/ggml/src/ggml-cpu/ggml-cpu-aarch64.c
-+++ b/ggml/src/ggml-cpu/ggml-cpu-aarch64.c
-@@ -4,7 +4,7 @@
- #include "ggml-quants.h"
- #include "ggml-impl.h"
- #include "ggml-cpu.h"
--#include "ggml-cpu/ggml-cpu-impl.h"
-+#include "ggml-cpu-impl.h"
- 
- #include <math.h>
- #include <string.h>
 diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
-index 111ff3b0..df0bd3c6 100644
+index bebff207..d6dd5600 100644
 --- a/ggml/src/ggml-cpu/ggml-cpu.c
 +++ b/ggml/src/ggml-cpu/ggml-cpu.c
 @@ -10,7 +10,7 @@
@@ -37,20 +23,21 @@ index 111ff3b0..df0bd3c6 100644
  
  #if defined(_MSC_VER) || defined(__MINGW32__)
 diff --git a/ggml/src/ggml-cpu/ggml-cpu.cpp b/ggml/src/ggml-cpu/ggml-cpu.cpp
-index 77e5d87a..91476ad0 100644
+index c390957a..1af5f7eb 100644
 --- a/ggml/src/ggml-cpu/ggml-cpu.cpp
 +++ b/ggml/src/ggml-cpu/ggml-cpu.cpp
-@@ -3,7 +3,7 @@
- #include "ggml-cpu.h"
+@@ -4,8 +4,7 @@
  #include "ggml-cpu-aarch64.h"
+ #include "ggml-cpu-traits.h"
  #include "ggml-impl.h"
 -#include "amx/amx.h"
+-
 +#include "amx.h"
  #include <cctype>
  #include <string>
  #include <vector>
 diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c
-index 7301a9c6..49ab3daf 100644
+index 7918388a..e2ed84e4 100644
 --- a/ggml/src/ggml-quants.c
 +++ b/ggml/src/ggml-quants.c
 @@ -3,7 +3,7 @@

llama/patches/0013-fix-missing-arg-in-static-assert-on-windows.patch

+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: jmorganca <jmorganca@gmail.com>
+Date: Sat, 14 Dec 2024 12:54:00 -0800
+Subject: [PATCH] fix missing arg in static assert on windows
+
+---
+ ggml/src/ggml-cuda/concat.cu | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/ggml/src/ggml-cuda/concat.cu b/ggml/src/ggml-cuda/concat.cu
+index 2f42b8a9..5eb9f08d 100644
+--- a/ggml/src/ggml-cuda/concat.cu
++++ b/ggml/src/ggml-cuda/concat.cu
+@@ -124,7 +124,7 @@ static __global__ void __launch_bounds__(CUDA_CONCAT_BLOCK_SIZE)
+           uint64_t   nb1,
+           uint64_t   nb2,
+           uint64_t   nb3){
+-    static_assert(dim >= 0 && dim <= 3);
++    static_assert(dim >= 0 && dim <= 3, "dim must be between 0 and 3");
+ 
+     const int64_t i3 = blockIdx.z;
+     const int64_t i2 = blockIdx.y;

llama/sampling.cpp

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/sampling.h

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/unicode-data.cpp

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/unicode-data.h

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/unicode.cpp

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/unicode.h

 /**
- * llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
+ * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
  *
  * MIT License
  *

llama/vendoring

-LLAMACPP_BASE_COMMIT=40c6d79fb52f995f47507fedfeaae2ac05d9b35c
+LLAMACPP_BASE_COMMIT=ba1cb19cdd0d92e012e0f6e009e0620f854b6afd

make/Makefile.rocm

@@ -86,7 +86,7 @@ GPU_COMPILER_CUFLAGS = \
 	-D_GNU_SOURCE \
 	-D_XOPEN_SOURCE=600 \
 	-DUSE_PROF_API=1 \
-	-std=gnu++14 \
+	-std=gnu++17 \
 	-x hip \
 	-mllvm=-amdgpu-early-inline-all=true \
 	-mllvm=-amdgpu-function-calls=false \

make/Makefile.sync

@@ -115,19 +115,19 @@ GGML_FILES= \
 	ggml/src/ggml-backend-impl.h \
 	ggml/include/ggml-alloc.h \
 	ggml/src/ggml-alloc.c \
-	ggml/src/ggml-aarch64.h \
-	ggml/src/ggml-aarch64.c \
 	ggml/include/ggml-blas.h \
 	ggml/include/ggml-cpp.h \
 	ggml/src/ggml-threading.cpp \
 	ggml/src/ggml-blas/ggml-blas.cpp \
 	ggml/src/ggml-cpu/ggml-cpu.c \
-	ggml/src/ggml-cpu/ggml-cpu-aarch64.c \
 	ggml/src/ggml-cpu/ggml-cpu.cpp \
 	ggml/src/ggml-cpu/ggml-cpu-aarch64.h \
+	ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp \
 	ggml/src/ggml-cpu/ggml-cpu-quants.h \
 	ggml/src/ggml-cpu/ggml-cpu-quants.c \
 	ggml/src/ggml-cpu/ggml-cpu-impl.h \
+	ggml/src/ggml-cpu/ggml-cpu-traits.h \
+	ggml/src/ggml-cpu/ggml-cpu-traits.cpp \
 	ggml/src/ggml-cpu/amx/amx.h \
 	ggml/src/ggml-cpu/amx/amx.cpp \
 	ggml/src/ggml-cpu/amx/mmq.cpp \

make/cuda.make

@@ -23,7 +23,7 @@ ifeq ($(OS),windows)
 else ifeq ($(OS),linux)
 	# On linux, nvcc requires avx512 -> -mavx512f -mavx512dq -mavx512bw
 	GPU_VECTOR_FLAGS=$(if $(filter avx512,$(GPU_RUNNER_CPU_FLAGS)),avx512f avx512dq avx512bw) $(filter-out avx512,$(GPU_RUNNER_CPU_FLAGS))
-	GPU_COMPILER_EXTRA_FLAGS = -fPIC -Wno-unused-function -std=c++11
+	GPU_COMPILER_EXTRA_FLAGS = -fPIC -Wno-unused-function -std=c++17
 	GPU_LIBS = $(sort $(wildcard $(addsuffix *.$(SHARED_EXT).*,$(addprefix $(GPU_LIB_DIR)/$(SHARED_PREFIX),$(GPU_RUNNER_LIBS_SHORT)))))
 	GPU_COMPILER_CFLAGS = $(CFLAGS) -Xcompiler -fPIC -D_GNU_SOURCE
 	GPU_COMPILER_CXXFLAGS = $(CXXFLAGS) -Xcompiler -fPIC -D_GNU_SOURCE

make/gpu.make

@@ -17,7 +17,7 @@ GPU_RUNNER_LIBS = $(wildcard $(addsuffix .$(SHARED_EXT).*,$(addprefix $(GPU_LIB_
 GPU_RUNNER_SRCS := \
 	$(filter-out $(wildcard llama/ggml-cuda/fattn*.cu),$(wildcard llama/ggml-cuda/*.cu)) \
 	$(wildcard llama/ggml-cuda/template-instances/mmq*.cu) \
-	llama/ggml.c llama/ggml-backend.cpp llama/ggml-alloc.c llama/ggml-quants.c llama/sgemm.cpp llama/ggml-aarch64.c llama/ggml-threading.cpp
+	llama/ggml.c llama/ggml-backend.cpp llama/ggml-alloc.c llama/ggml-quants.c llama/sgemm.cpp llama/ggml-threading.cpp
 GPU_RUNNER_HDRS := \
 	$(wildcard llama/ggml-cuda/*.cuh)