vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 23:49:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	CODEOWNERS
#	common/CMakeLists.txt
#	common/common.h
#	docs/ops.md
#	docs/ops/Metal.csv
#	examples/batched/CMakeLists.txt
#	examples/convert-llama2c-to-ggml/CMakeLists.txt
#	examples/debug/CMakeLists.txt
#	examples/diffusion/CMakeLists.txt
#	examples/embedding/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/gen-docs/CMakeLists.txt
#	examples/idle/CMakeLists.txt
#	examples/lookahead/CMakeLists.txt
#	examples/lookup/CMakeLists.txt
#	examples/parallel/CMakeLists.txt
#	examples/passkey/CMakeLists.txt
#	examples/retrieval/CMakeLists.txt
#	examples/save-load-state/CMakeLists.txt
#	examples/speculative-simple/CMakeLists.txt
#	examples/speculative/CMakeLists.txt
#	examples/sycl/CMakeLists.txt
#	examples/training/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	pocs/vdot/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/test-quantize-stats.cpp
#	tools/batched-bench/CMakeLists.txt
#	tools/cli/CMakeLists.txt
#	tools/cli/cli.cpp
#	tools/completion/CMakeLists.txt
#	tools/cvector-generator/CMakeLists.txt
#	tools/cvector-generator/cvector-generator.cpp
#	tools/export-lora/CMakeLists.txt
#	tools/gguf-split/CMakeLists.txt
#	tools/gguf-split/gguf-split.cpp
#	tools/imatrix/CMakeLists.txt
#	tools/llama-bench/CMakeLists.txt
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/perplexity/CMakeLists.txt
#	tools/quantize/CMakeLists.txt
#	tools/quantize/quantize.cpp
#	tools/results/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/tokenize/CMakeLists.txt
#	tools/tts/CMakeLists.txt
This commit is contained in:
Concedo 2026-04-17 22:37:37 +08:00
commit 79882d669a
146 changed files with 1507 additions and 2103 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tools/server/server-common.cpp
View file

@ -84,12 +84,16 @@ std::string gen_tool_call_id() {
return random_string();
}
static std::string media_marker = "";
const char * get_media_marker() {
if (media_marker.empty()) {
media_marker = "<__media_" + random_string() + "__>";
}
return media_marker.c_str();
static const std::string marker = []() {
// allow user to pin a reproducible marker via env var
const char * env = getenv("LLAMA_MEDIA_MARKER");
if (env && env[0] != '\0') {
return std::string(env);
}
return std::string("<__media_") + random_string() + "__>";
}();
return marker.c_str();
}
//

3
tools/server/server-context.cpp
View file

@ -4,6 +4,7 @@
#include "server-task.h"
#include "server-queue.h"
#include "build-info.h"
#include "common.h"
#include "llama.h"
#include "log.h"
@ -3010,7 +3011,7 @@ server_context_meta server_context::get_meta() const {
auto eos_token_str = eos_id != LLAMA_TOKEN_NULL ? common_token_to_piece(impl->ctx, eos_id, true) : "";
return server_context_meta {
/* build_info */ build_info,
/* build_info */ std::string(llama_build_info()),
/* model_name */ impl->model_name,
/* model_aliases */ impl->model_aliases,
/* model_tags */ impl->model_tags,

3
tools/server/server-models.cpp
View file

@ -1,6 +1,7 @@
#include "server-common.h"
#include "server-models.h"
#include "build-info.h"
#include "preset.h"
#include "download.h"
@ -936,7 +937,7 @@ void server_models_routes::init_routes() {
{"n_ctx", 0},
}},
{"webui_settings", webui_settings},
{"build_info", build_info},
{"build_info", std::string(llama_build_info())},
});
return res;
}

15
tools/server/server-task.cpp
View file

@ -1,5 +1,6 @@
#include "server-task.h"
#include "build-info.h"
#include "chat.h"
#include "common.h"
#include "json-schema-to-grammar.h"
@ -791,7 +792,7 @@ json server_task_result_cmpl_final::to_json_oaicompat() {
})},
{"created", t},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "text_completion"},
{"usage", usage_json_oaicompat()},
{"id", oaicompat_cmpl_id}
@ -839,7 +840,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat() {
{"choices", json::array({choice})},
{"created", t},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "chat.completion"},
{"usage", usage_json_oaicompat()},
{"id", oaicompat_cmpl_id}
@ -876,7 +877,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
{"created", t},
{"id", oaicompat_cmpl_id},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "chat.completion.chunk"},
});
}
@ -892,7 +893,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
{"created", t},
{"id", oaicompat_cmpl_id},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "chat.completion.chunk"},
});
@ -904,7 +905,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
{"created", t},
{"id", oaicompat_cmpl_id},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "chat.completion.chunk"},
{"usage", usage_json_oaicompat()},
});
@ -1469,7 +1470,7 @@ json server_task_result_cmpl_partial::to_json_oaicompat() {
})},
{"created", t},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "text_completion"},
{"id", oaicompat_cmpl_id}
};
@ -1506,7 +1507,7 @@ json server_task_result_cmpl_partial::to_json_oaicompat_chat() {
{"created", t},
{"id", oaicompat_cmpl_id},
{"model", oaicompat_model},
{"system_fingerprint", build_info},
{"system_fingerprint", std::string(llama_build_info())},
{"object", "chat.completion.chunk"},
});
};

3
tools/server/server.cpp
View file

@ -5,6 +5,7 @@
#include "server-tools.h"
#include "arg.h"
#include "build-info.h"
#include "common.h"
#include "llama.h"
#include "log.h"
@ -108,7 +109,7 @@ int main(int argc, char ** argv) {
llama_backend_init();
llama_numa_init(params.numa);
LOG_INF("build_info: %s\n", build_info.c_str());
LOG_INF("build_info: %s\n", llama_build_info());
LOG_INF("%s\n", common_params_get_system_info(params).c_str());
server_http_context ctx_http;

1
tools/server/tests/unit/test_vision_api.py
View file

@ -37,6 +37,7 @@ JSON_PROMPT_STRING_KEY = "prompt_string"
@pytest.fixture(autouse=True)
def create_server():
global server
os.environ['LLAMA_MEDIA_MARKER'] = '<__media__>'
server = ServerPreset.tinygemma3()
def test_models_supports_multimodal_capability():