vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	examples/llama.android/llama/src/main/cpp/CMakeLists.txt
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	grammars/README.md
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	tests/test-chat-template.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
This commit is contained in:
Concedo 2024-06-30 10:59:42 +08:00
commit 02f92f6ecc
22 changed files with 632 additions and 182 deletions
Download patch file Download diff file Expand all files Collapse all files

16
examples/server/server.cpp
View file

@ -2021,6 +2021,7 @@ struct server_context {
slot.t_start_generation = 0;
if (slot.infill) {
const bool add_bos = llama_should_add_bos_token(model);
bool suff_rm_leading_spc = true;
if (params.input_suffix.find_first_of(' ') == 0 && params.input_suffix.size() > 1) {
params.input_suffix.erase(0, 1);
@ -2036,16 +2037,21 @@ struct server_context {
}
prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(model));
prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(model)); // always add BOS
prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(model));
prefix_tokens.insert(prefix_tokens.end(), suffix_tokens.begin(), suffix_tokens.end());
suffix_tokens.insert(suffix_tokens.begin(), llama_token_suffix(model));
auto embd_inp = params.spm_infill ? suffix_tokens : prefix_tokens;
auto embd_end = params.spm_infill ? prefix_tokens : suffix_tokens;
if (add_bos) {
embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
}
embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
const llama_token middle_token = llama_token_middle(model);
if (middle_token >= 0) {
prefix_tokens.push_back(middle_token);
embd_inp.push_back(middle_token);
}
prompt_tokens = prefix_tokens;
prompt_tokens = embd_inp;
} else {
prompt_tokens = tokenize(slot.prompt, system_prompt.empty()); // add BOS if there isn't system prompt
}