Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	AGENTS.md
#	CODEOWNERS
#	CONTRIBUTING.md
#	docs/backend/OPENCL.md
#	docs/development/HOWTO-add-model.md
#	examples/training/finetune.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-fa-kernels.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/compare-llama-bench.py
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	scripts/sync_vendor.py
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-model-load-cancel.cpp
#	tests/test-quantize-stats.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
This commit is contained in:
Concedo
2026-07-25 12:20:51 +08:00
81 changed files with 40233 additions and 848 deletions
+14 -5
View File
@@ -2192,9 +2192,10 @@ static common_chat_params common_chat_params_init_cohere2moe(const common_chat_t
{ COMMON_CHAT_ROLE_SYSTEM, TURN_START + SYSTEM },
};
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
auto include_grammar = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE;
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
auto has_response_format = inputs.json_schema.is_object() && !inputs.json_schema.empty();
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);
if (inputs.has_continuation()) {
const auto & msg = inputs.continue_msg;
@@ -2225,7 +2226,11 @@ static common_chat_params common_chat_params_init_cohere2moe(const common_chat_t
p.optional(p.literal(THINK_END))));
}
auto text_content = p.literal(TEXT_START) + p.content(p.until(TEXT_END)) + p.optional(p.literal(TEXT_END));
auto text_content = has_response_format
? p.literal(TEXT_START) +
p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)) +
p.optional(p.literal(TEXT_END))
: p.literal(TEXT_START) + p.content(p.until(TEXT_END)) + p.optional(p.literal(TEXT_END));
if (!has_tools || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) {
return generation_prompt + reasoning + text_content + p.optional(p.literal(TURN_END)) + end;
@@ -2253,13 +2258,17 @@ static common_chat_params common_chat_params_init_cohere2moe(const common_chat_t
data.parser = parser.save();
if (include_grammar) {
data.grammar_lazy = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_AUTO;
data.grammar_lazy = !has_response_format && inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_AUTO;
data.grammar = build_grammar([&](const common_grammar_builder & builder) {
foreach_function(inputs.tools, [&](const json & tool) {
const auto & function = tool.at("function");
auto schema = function.at("parameters");
builder.resolve_refs(schema);
});
if (has_response_format) {
auto schema = inputs.json_schema;
builder.resolve_refs(schema);
}
parser.build_grammar(builder, data.grammar_lazy);
});