CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

gpt-oss: implement harmony parsing (#15181)

Browse Source 
* model : add harmony parser for gpt-oss

* gpt-oss : fix grammar trigger from causing empty stack

* gpt-oss: tweak the grammar trigger again

* gpt-oss : add support for recipient in role header

* gpt-oss : fix ungrouped tool calls in grammar

* gpt-oss : loosen function name matching during parse

* gpt-oss : clean up workarounds

* gpt-oss : add template tests

* gpt-oss : simulate thinking and tool call tags

* gpt-oss : undo think tags when reasoning_format is none

* gpt-oss : set special tokens back to user defined

* gpt-oss : update openai-gpt-oss template

* server : filter out harmony thought messages

* gpt-oss : simplify parsing
This commit is contained in:
Aldehir Rojas
2025-08-14 09:23:11 -05:00
committed by GitHub
parent 646944cfa8
commit b204a5a234
7 changed files with 672 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-vocab.cpp
View File

@@ -2341,7 +2341,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
// @ngxson : quick hack for gpt-oss, always render these tokens
for (const auto & t : token_to_id) {
if (t.first == "<|channel|>" || t.first == "<|message|>" || t.first == "<|start|>") {
if (t.first == "<|channel|>" || t.first == "<|message|>" || t.first == "<|start|>" || t.first == "<|constrain|>") {
id_to_token[t.second].attr = LLAMA_TOKEN_ATTR_USER_DEFINED;
}
}
@@ -2388,6 +2388,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
if (has_return && has_call && has_end) {
special_eog_ids.erase(end_id);
id_to_token[end_id].attr = LLAMA_TOKEN_ATTR_USER_DEFINED;
LLAMA_LOG_WARN("%s: special_eog_ids contains both '<|return|>' and '<|call|>' tokens, removing '<|end|>' token from EOG list\n", __func__);
}
}