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

chat : add new template for DeepSeek V4 Flash 0731 (#26398)

Browse Source 
* common/chat: update DeepSeek V4 templates

Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of this change.

- Default drop_thinking for DeepSeek V4 history so prior thinking is omitted unless preserve_reasoning is requested or tools are present.
- Add structured output response-format instructions to the V4 templates and pass the schema into template rendering.
- Add a separate Flash 0731 template for the updated high and max reasoning effort mapping.
- Cover reasoning effort, drop_thinking, structured output prompts, preserved reasoning, continuations, and empty tool arguments in template rendering tests.

Official references:
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/encoding/encoding_dsv4.py
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/encoding/encoding_dsv4.py

Assisted-by: Codex

* Fix deepseek v4 0731 template selection

* remove unneeded lower normalization

* Fix DSML parser to consume the tool call separator

* address aldehir requests

* address aldehir comment
This commit is contained in:
Thiago Padilha
2026-08-03 17:59:11 -05:00
committed by GitHub
parent 94bc47f280
commit 0ef6e55edb
6 changed files with 363 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+26 -7
View File
@@ -2114,6 +2114,11 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
auto include_grammar = has_response_format || (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE);
std::optional<json> additional_context;
if (is_v4 && has_response_format) {
additional_context = json{ { "response_format", inputs.json_schema } };
}
const std::string DSML = "｜DSML｜";
const std::string THINK_START = "<think>";
const std::string THINK_END = "</think>";
@@ -2125,9 +2130,12 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
const std::string PARAM_START = "<" + DSML + "parameter";
const std::string PARAM_END = "</" + DSML + "parameter>";
const std::string GEN_PROMPT = "<｜Assistant｜>";
const std::string TC_SEPARATOR = "\n\n";
data.prompt = common_chat_template_direct_apply_impl(tmpl, inputs, adjusted_messages);
data.generation_prompt = common_chat_template_generation_prompt_impl(tmpl, inputs, adjusted_messages);
data.prompt = common_chat_template_direct_apply_impl(
tmpl, inputs, adjusted_messages, std::nullopt, additional_context);
data.generation_prompt = common_chat_template_generation_prompt_impl(
tmpl, inputs, adjusted_messages, std::nullopt, additional_context);
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
data.supports_thinking = true;
data.thinking_start_tag = THINK_START;
@@ -2141,9 +2149,16 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
if (inputs.has_continuation()) {
const auto & msg = inputs.continue_msg;
data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content;
if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
data.generation_prompt += THINK_END + msg.render_content();
if (is_v4 && msg.reasoning_content.empty()) {
data.generation_prompt = GEN_PROMPT + THINK_END;
if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
data.generation_prompt += msg.render_content();
}
} else {
data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content;
if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
data.generation_prompt += THINK_END + msg.render_content();
}
}
data.prompt += data.generation_prompt;
@@ -2242,7 +2257,9 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
if (extract_reasoning && inputs.enable_thinking) {
reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END);
reasoning_with_tc = THINK_START + p.reasoning(p.until_one_of({ FC_START, THINK_END })) + obligatory_tool_calls;
reasoning_with_tc = THINK_START +
p.reasoning(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START, THINK_END })) +
p.space() + obligatory_tool_calls;
allow_reasoning_with_tc = true;
} else if (extract_reasoning) {
// Thinking disabled but reasoning extraction requested: the generation prompt
@@ -2265,7 +2282,9 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
return generation_prompt + reasoning + p.content(p.rest()) + end;
}
auto content_before_tools = p.negate(p.literal(THINK_START)) + p.content(p.until(FC_START));
auto content_before_tools = p.negate(p.literal(THINK_START)) +
p.content(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START })) +
p.space();
return allow_reasoning_with_tc ? generation_prompt + (reasoning_with_tc | (reasoning + content_before_tools + tool_calls)) + end :
generation_prompt + reasoning + content_before_tools + tool_calls + end;
});
common/jinja/caps.cpp
+1
View File
@@ -482,6 +482,7 @@ caps caps_get(jinja::program & prog) {
});
},
[&](context & ctx) {
ctx.set_val("enable_thinking", mk_val<value_bool>(true));
caps_apply_preserve_reasoning(ctx, true);
},
nullptr, // tools_fn