Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

Browse Source 
* common : extract trie/ac to a separate file

* common : support multiple token sequences in the reasoning budget sampler

* common/trie : return matched word index

* common/trie : rename "word" to "pattern"

* common/reasoning-budget : expose matched end sequence

* common/sampling : replay end sequence when reasoning budget is done

* cont : update to use multiple end sequences

* cont : clean up
This commit is contained in:
Aldehir Rojas
2026-07-25 11:58:09 +02:00
committed by GitHub
parent d67c0b4107
commit 910196f6b3
14 changed files with 497 additions and 254 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+14 -8
View File
@@ -1024,7 +1024,7 @@ static common_chat_params common_chat_params_init_ministral_3(const common_chat_
data.supports_thinking = true;
data.thinking_start_tag = "[THINK]";
data.thinking_end_tag = "[/THINK]";
data.thinking_end_tags = {"[/THINK]"};
data.prompt = common_chat_template_direct_apply_impl(tmpl, inputs, /* messages_override = */ adjusted_messages);
data.generation_prompt = common_chat_template_generation_prompt_impl(tmpl, inputs, /* messages_override = */ adjusted_messages);
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
@@ -1150,6 +1150,9 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
data.supports_thinking = true;
data.thinking_start_tag = "<|channel|>analysis<|message|>";
data.thinking_end_tags = {"<|end|>"};
// These special tokens are required to parse properly, so we include them
// even if parse_tool_calls is false.
data.preserved_tokens = {
@@ -1294,7 +1297,7 @@ static common_chat_params common_chat_params_init_gemma4(const common_chat_templ
data.format = COMMON_CHAT_FORMAT_PEG_GEMMA4;
data.supports_thinking = true;
data.thinking_start_tag = "<|channel>thought";
data.thinking_end_tag = "<channel|>";
data.thinking_end_tags = {"<channel|>"};
data.preserved_tokens = {
"<|channel>",
@@ -1569,7 +1572,7 @@ static common_chat_params common_chat_params_init_kimi_k2(const common_chat_temp
const std::string GEN_PROMPT = "<|im_assistant|>assistant<|im_middle|>";
data.thinking_start_tag = THINK_START;
data.thinking_end_tag = THINK_END;
data.thinking_end_tags = {THINK_END};
if (inputs.has_continuation()) {
const auto & msg = inputs.continue_msg;
@@ -1703,7 +1706,7 @@ static common_chat_params common_chat_params_init_lfm2(const common_chat_templat
}
data.thinking_start_tag = THINK_START;
data.thinking_end_tag = THINK_END;
data.thinking_end_tags = {THINK_END};
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
auto has_response_format = !inputs.json_schema.is_null() && inputs.json_schema.is_object();
@@ -1943,7 +1946,7 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
data.supports_thinking = true;
data.thinking_start_tag = "<think>";
data.thinking_end_tag = "</think>";
data.thinking_end_tags = {"</think>"};
data.preserved_tokens = {
"｜DSML｜",
"<think>",
@@ -2160,7 +2163,7 @@ static common_chat_params common_chat_params_init_cohere2moe(const common_chat_t
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
data.supports_thinking = true;
data.thinking_start_tag = THINK_START;
data.thinking_end_tag = THINK_END;
data.thinking_end_tags = {THINK_END};
data.preserved_tokens = {
TURN_START, TURN_END, CHATBOT, USER, SYSTEM,
THINK_START, THINK_END,
@@ -2510,7 +2513,7 @@ static common_chat_params common_chat_params_init_minicpm5(const common_chat_tem
};
data.thinking_start_tag = "<think>";
data.thinking_end_tag = "</think>";
data.thinking_end_tags = {"</think>"};
data.message_delimiters = {
{ COMMON_CHAT_ROLE_ASSISTANT, "<|im_start|>assistant" },
@@ -2866,7 +2869,10 @@ static common_chat_params common_chat_templates_apply_jinja(const struct common_
auto_params.supports_thinking = autoparser.reasoning.mode != autoparser::reasoning_mode::NONE;
if (auto_params.supports_thinking) {
auto_params.thinking_start_tag = trim_whitespace(autoparser.reasoning.start);
auto_params.thinking_end_tag = trim_whitespace(autoparser.reasoning.end);
auto end_tag = trim_whitespace(autoparser.reasoning.end);
if (!end_tag.empty()) {
auto_params.thinking_end_tags = {std::move(end_tag)};
}
}
common_peg_arena arena;
arena.load(auto_params.parser);