backend: rebase llama.cpp submodule on latest upstream (#2694)

* Adds support for GPT-NeoX, Gemma 2, OpenELM, ChatGLM, and Jais architectures (all with Kompute support)
* Also enables Kompute support for StarCoder2, XVERSE, Command R, and OLMo
* Includes a number of Kompute resource management fixes

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

gpt4all-backend/CMakeLists.txt

@@ -90,25 +90,25 @@ foreach(BUILD_VARIANT IN LISTS BUILD_VARIANTS)
     else()
         set(GPT4ALL_ALLOW_NON_AVX ON)
     endif()
-    set(LLAMA_AVX2 ${GPT4ALL_ALLOW_NON_AVX})
-    set(LLAMA_F16C ${GPT4ALL_ALLOW_NON_AVX})
-    set(LLAMA_FMA  ${GPT4ALL_ALLOW_NON_AVX})
-
-    set(LLAMA_METAL   OFF)
-    set(LLAMA_KOMPUTE OFF)
-    set(LLAMA_VULKAN  OFF)
-    set(LLAMA_CUDA    OFF)
-    set(LLAMA_ROCM    OFF)
+    set(GGML_AVX2 ${GPT4ALL_ALLOW_NON_AVX})
+    set(GGML_F16C ${GPT4ALL_ALLOW_NON_AVX})
+    set(GGML_FMA  ${GPT4ALL_ALLOW_NON_AVX})
+
+    set(GGML_METAL   OFF)
+    set(GGML_KOMPUTE OFF)
+    set(GGML_VULKAN  OFF)
+    set(GGML_CUDA    OFF)
+    set(GGML_ROCM    OFF)
     if (BUILD_VARIANT MATCHES metal)
-        set(LLAMA_METAL   ON)
+        set(GGML_METAL   ON)
     elseif (BUILD_VARIANT MATCHES kompute)
-        set(LLAMA_KOMPUTE ON)
+        set(GGML_KOMPUTE ON)
     elseif (BUILD_VARIANT MATCHES vulkan)
-        set(LLAMA_VULKAN  ON)
+        set(GGML_VULKAN  ON)
     elseif (BUILD_VARIANT MATCHES cuda)
-        set(LLAMA_CUDA    ON)
+        set(GGML_CUDA    ON)
     elseif (BUILD_VARIANT MATCHES rocm)
-        set(LLAMA_HIPBLAS ON)
+        set(GGML_HIPBLAS ON)
     endif()
 
     # Include GGML