vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : refactor src/llama.cpp (#10902)

Browse source 
* llama : scatter llama.cpp into multiple modules (wip)

* llama : control-vector -> adapter

* llama : arch

* llama : mmap

ggml-ci

* ci : remove BUILD_SHARED_LIBS=OFF

ggml-ci

* llama : arch (cont)

ggml-ci

* llama : chat

ggml-ci

* llama : model

ggml-ci

* llama : hparams

ggml-ci

* llama : adapter

ggml-ci

* examples : fix

ggml-ci

* rebase

ggml-ci

* minor

* llama : kv cache

ggml-ci

* llama : impl

ggml-ci

* llama : batch

ggml-ci

* cont

ggml-ci

* llama : context

ggml-ci

* minor

* llama : context (cont)

ggml-ci

* llama : model loader

ggml-ci

* common : update lora

ggml-ci

* llama : quant

ggml-ci

* llama : quant (cont)

ggml-ci

* minor [no ci]
This commit is contained in:
Georgi Gerganov 2025-01-03 10:18:53 +02:00 • committed by GitHub
parent 2f0ee84b9b
commit f66f582927
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
61 changed files with 12193 additions and 11649 deletions
Download patch file Download diff file Expand all files Collapse all files

14
examples/server/utils.hpp
View file

@ -799,25 +799,25 @@ static std::vector<llama_token_data> get_token_probabilities(llama_context * ctx
}
static bool are_lora_equal(
const std::vector<common_lora_adapter_container> & l1,
const std::vector<common_lora_adapter_container> & l2) {
const std::vector<common_lora_adapter_info> & l1,
const std::vector<common_lora_adapter_info> & l2) {
if (l1.size() != l2.size()) {
return false;
}
for (size_t i = 0; i < l1.size(); ++i) {
// we don't check lora.path to reduce the time complexity
if (l1[i].scale != l2[i].scale || l1[i].adapter != l2[i].adapter) {
if (l1[i].scale != l2[i].scale || l1[i].ptr != l2[i].ptr) {
return false;
}
}
return true;
}
// parse lora config from JSON request, returned a copy of base_lora with updated scale
static std::vector<common_lora_adapter_container> parse_lora_request(
const std::vector<common_lora_adapter_container> & base_lora,
// parse lora config from JSON request, returned a copy of lora_base with updated scale
static std::vector<common_lora_adapter_info> parse_lora_request(
const std::vector<common_lora_adapter_info> & lora_base,
const json & data) {
std::vector<common_lora_adapter_container> lora(base_lora);
std::vector<common_lora_adapter_info> lora(lora_base);
int max_idx = lora.size();
// clear existing value