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>
86 lines
2.0 KiB
C++
Vendored
86 lines
2.0 KiB
C++
Vendored
#include "llama-hparams.h"
|
|
|
|
#include "ggml.h"
|
|
|
|
#include <algorithm>
|
|
|
|
uint32_t llama_hparams::n_head(uint32_t il) const {
|
|
if (il < n_layer) {
|
|
return n_head_arr[il];
|
|
}
|
|
|
|
GGML_ABORT("fatal error");
|
|
}
|
|
|
|
uint32_t llama_hparams::n_head_kv(uint32_t il) const {
|
|
if (il < n_layer) {
|
|
return n_head_kv_arr[il];
|
|
}
|
|
|
|
GGML_ABORT("fatal error");
|
|
}
|
|
|
|
uint32_t llama_hparams::n_ff(uint32_t il) const {
|
|
if (il < n_layer) {
|
|
return n_ff_arr[il];
|
|
}
|
|
|
|
GGML_ABORT("fatal error");
|
|
}
|
|
|
|
uint32_t llama_hparams::n_gqa(uint32_t il) const {
|
|
const uint32_t n_head = this->n_head(il);
|
|
const uint32_t n_head_kv = this->n_head_kv(il);
|
|
|
|
if (n_head_kv == 0) {
|
|
return 0;
|
|
}
|
|
|
|
return n_head/n_head_kv;
|
|
}
|
|
|
|
uint32_t llama_hparams::n_embd_k_gqa(uint32_t il) const {
|
|
const uint32_t n_head_kv = this->n_head_kv(il);
|
|
|
|
return n_embd_head_k * n_head_kv;
|
|
}
|
|
|
|
uint32_t llama_hparams::n_embd_v_gqa(uint32_t il) const {
|
|
const uint32_t n_head_kv = this->n_head_kv(il);
|
|
|
|
return n_embd_head_v * n_head_kv;
|
|
}
|
|
|
|
uint32_t llama_hparams::n_embd_k_s() const {
|
|
if (wkv_head_size != 0) {
|
|
// for RWKV models
|
|
return 2 * n_embd;
|
|
}
|
|
|
|
// TODO: maybe support other convolution strides than 1
|
|
// NOTE: since the first column of the conv_state is shifted out each time, it's not actually needed
|
|
return (ssm_d_conv > 0 ? ssm_d_conv - 1 : 0) * ssm_d_inner;
|
|
}
|
|
|
|
uint32_t llama_hparams::n_embd_v_s() const {
|
|
if (wkv_head_size != 0) {
|
|
// corresponds to RWKV's wkv_states size
|
|
return n_embd * wkv_head_size;
|
|
}
|
|
|
|
// corresponds to Mamba's ssm_states size
|
|
return ssm_d_state * ssm_d_inner;
|
|
}
|
|
|
|
bool llama_hparams::n_bskcn(uint32_t n, uint32_t il) const {
|
|
if (il < n_layer) {
|
|
return n_bskcn_arr[n][il] > 0;
|
|
}
|
|
|
|
GGML_ABORT("fatal error");
|
|
}
|
|
|
|
bool llama_hparams::cross_attention_layers(uint32_t il) const {
|
|
return std::find(cross_attn_layers.begin(), cross_attn_layers.end(), il) != cross_attn_layers.end();
|
|
}
|