mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-15 18:27:08 +00:00
dcfb7a105c
* 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>
67 lines
1.5 KiB
C++
Vendored
67 lines
1.5 KiB
C++
Vendored
#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);
|
|
};
|