vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 02:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Support diffusion models: Add Dream 7B (#14644)

Browse source 
* Support diffusion models: Add Dream 7B

* Move diffusion to examples

* Move stuff to examples. Add patch to not use kv-cache

* Address review comments

* Make sampling fast

* llama: remove diffusion functions

* Add basic timings + cleanup

* More cleanup

* Review comments: better formating, use LOG instead std::cerr, re-use batch, use ubatch instead of max_length

* fixup!

* Review: move everything to diffusion-cli for now
This commit is contained in:
Aman Gupta 2025-07-16 20:03:51 +08:00 • committed by GitHub
parent 64978340b0
commit ab14019821
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 804 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama-vocab.cpp
View file

@ -3354,6 +3354,10 @@ llama_token llama_vocab::token_fim_sep() const {
return pimpl->special_fim_sep_id;
}
llama_token llama_vocab::token_mask() const {
return pimpl->special_mask_id;
}
bool llama_vocab::get_add_space_prefix() const {
return pimpl->add_space_prefix;
}
@ -3594,6 +3598,10 @@ llama_token llama_vocab_fim_sep(const struct llama_vocab * vocab) {
return vocab->token_fim_sep();
}
llama_token llama_vocab_mask(const struct llama_vocab* vocab) {
return vocab->token_mask();
}
// deprecated
const char * llama_token_get_text(const struct llama_vocab * vocab, llama_token token) {
return llama_vocab_get_text(vocab, token);