next build (#8539)

* add build to .dockerignore

* test: only build one arch

* add build to .gitignore

* fix ccache path

* filter amdgpu targets

* only filter if autodetecting

* Don't clobber gpu list for default runner

This ensures the GPU specific environment variables are set properly

* explicitly set CXX compiler for HIP

* Update build_windows.ps1

This isn't complete, but is close.  Dependencies are missing, and it only builds the "default" preset.

* build: add ollama subdir

* add .git to .dockerignore

* docs: update development.md

* update build_darwin.sh

* remove unused scripts

* llm: add cwd and build/lib/ollama to library paths

* default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS

* add additional cmake output vars for msvc

* interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12

* remove unncessary filepath.Dir, cleanup

* add hardware-specific directory to path

* use absolute server path

* build: linux arm

* cmake install targets

* remove unused files

* ml: visit each library path once

* build: skip cpu variants on arm

* build: install cpu targets

* build: fix workflow

* shorter names

* fix rocblas install

* docs: clean up development.md

* consistent build dir removal in development.md

* silence -Wimplicit-function-declaration build warnings in ggml-cpu

* update readme

* update development readme

* llm: update library lookup logic now that there is one runner (#8587)

* tweak development.md

* update docs

* add windows cuda/rocm tests

---------

Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>

llama/llama.cpp/src/llama-adapter.h

@@ -0,0 +1,66 @@
+#pragma once
+
+#include "llama-impl.h"
+#include "llama-hparams.h"
+
+#include "ggml-cpp.h"
+
+#include <unordered_map>
+#include <vector>
+
+//
+// llama_adapter_cvec
+//
+
+// TODO: rename to llama_adapter_cvec
+struct llama_control_vector {
+    std::vector<ggml_context_ptr> ctxs;
+    std::vector<ggml_backend_buffer_ptr> bufs;
+
+    std::vector<struct ggml_tensor *> tensors; // per layer
+
+    int32_t layer_start = -1;
+    int32_t layer_end   = -1;
+
+    struct ggml_tensor * tensor_for(int il) const;
+
+    struct ggml_tensor * apply_to(struct ggml_context * ctx, struct ggml_tensor * cur, int  il) const;
+};
+
+int32_t llama_control_vector_apply(
+        struct llama_control_vector & cvec,
+        const llama_model & model,
+        const float * data,
+        size_t len,
+        int32_t n_embd,
+        int32_t il_start,
+        int32_t il_end);
+
+//
+// llama_adapter_lora
+//
+
+// TODO: rename to llama_adapter_lora_weight
+struct llama_lora_weight {
+    struct ggml_tensor * a = nullptr;
+    struct ggml_tensor * b = nullptr;
+
+    llama_lora_weight() = default;
+    llama_lora_weight(struct ggml_tensor * a, struct ggml_tensor * b) : a(a), b(b) {}
+};
+
+// TODO: rename to llama_adapter_lora
+struct llama_lora_adapter {
+    // map tensor name to lora_a_b
+    std::unordered_map<std::string, struct llama_lora_weight> ab_map;
+
+    std::vector<ggml_context_ptr> ctxs;
+    std::vector<ggml_backend_buffer_ptr> bufs;
+
+    float alpha;
+
+    llama_lora_adapter() = default;
+    ~llama_lora_adapter() = default;
+
+    llama_lora_weight * get_weight(struct ggml_tensor * w);
+};