mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-19 01:05:09 +02:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .devops/intel.Dockerfile # .github/workflows/build-android.yml # .github/workflows/build.yml # .github/workflows/release.yml # .gitignore # docs/backend/SYCL.md # docs/backend/snapdragon/README.md # examples/model-conversion/scripts/causal/convert-model.sh # ggml/CMakeLists.txt # ggml/src/CMakeLists.txt # ggml/src/ggml-hexagon/ggml-hexagon.cpp # ggml/src/ggml-hexagon/htp/CMakeLists.txt # ggml/src/ggml-hexagon/htp/hex-utils.h # ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c # ggml/src/ggml-hexagon/htp/htp-ctx.h # ggml/src/ggml-hexagon/htp/htp-ops.h # ggml/src/ggml-hexagon/htp/htp_iface.idl # ggml/src/ggml-hexagon/htp/hvx-base.h # ggml/src/ggml-hexagon/htp/main.c # ggml/src/ggml-hexagon/htp/matmul-ops.c # ggml/src/ggml-hexagon/libggml-htp.inf # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-sycl/mmvq.cpp # ggml/src/ggml-sycl/mmvq.hpp # ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_blk.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl # scripts/server-test-structured.py # scripts/snapdragon/adb/run-bench.sh # scripts/snapdragon/adb/run-cli.sh # scripts/snapdragon/adb/run-completion.sh # scripts/snapdragon/adb/run-mtmd.sh # scripts/snapdragon/adb/run-tool.sh # scripts/snapdragon/qdc/requirements.txt # scripts/snapdragon/windows/run-bench.ps1 # scripts/snapdragon/windows/run-cli.ps1 # scripts/snapdragon/windows/run-completion.ps1 # scripts/snapdragon/windows/run-mtmd.ps1 # scripts/snapdragon/windows/run-tool.ps1 # tests/test-backend-ops.cpp # tools/cli/cli.cpp # ty.toml
This commit is contained in:
+21
-5
@@ -558,6 +558,26 @@ bool common_chat_templates_was_explicit(const struct common_chat_templates * tmp
|
||||
return tmpls->has_explicit_template;
|
||||
}
|
||||
|
||||
// LFM2 format detection: template uses <|tool_list_start|>[...]<|tool_list_end|> around the tool list
|
||||
// and <|tool_call_start|>[...]<|tool_call_end|> around each tool call
|
||||
static bool is_lfm2_template(const std::string & src) {
|
||||
return src.find("<|tool_list_start|>") != std::string::npos &&
|
||||
src.find("<|tool_list_end|>") != std::string::npos;
|
||||
}
|
||||
|
||||
common_chat_prompt_preset common_chat_get_asr_prompt(const common_chat_templates * chat_templates) {
|
||||
common_chat_prompt_preset asr_preset;
|
||||
asr_preset.system = "";
|
||||
asr_preset.user = "Transcribe audio to text";
|
||||
|
||||
if (chat_templates && chat_templates->template_default && is_lfm2_template(chat_templates->template_default->source())) {
|
||||
asr_preset.system = "Perform ASR.";
|
||||
asr_preset.user = "";
|
||||
}
|
||||
|
||||
return asr_preset;
|
||||
}
|
||||
|
||||
std::string common_chat_templates_source(const struct common_chat_templates * tmpls, const std::string & variant) {
|
||||
if (!variant.empty()) {
|
||||
if (variant == "tool_use") {
|
||||
@@ -2067,10 +2087,7 @@ std::optional<common_chat_params> common_chat_try_specialized_template(
|
||||
return common_chat_params_init_kimi_k2(tmpl, params);
|
||||
}
|
||||
|
||||
// LFM2 format detection: template uses <|tool_list_start|>[...]<|tool_list_end|> around the tool list
|
||||
// and <|tool_call_start|>[...]<|tool_call_end|> around each tool call
|
||||
if (src.find("<|tool_list_start|>") != std::string::npos &&
|
||||
src.find("<|tool_list_end|>") != std::string::npos) {
|
||||
if (is_lfm2_template(src)) {
|
||||
LOG_DBG("Using specialized template: LFM2\n");
|
||||
return common_chat_params_init_lfm2(tmpl, params);
|
||||
}
|
||||
@@ -2379,4 +2396,3 @@ std::map<std::string, bool> common_chat_templates_get_caps(const common_chat_tem
|
||||
GGML_ASSERT(chat_templates->template_default != nullptr);
|
||||
return chat_templates->template_default->caps.to_map();
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user