Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '763d06edb7dd5094ea58bad1d81e2e8d35033e34' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-linux-cross.yml
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/mtmd/mtmd.cpp
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo
2025-05-31 12:44:18 +08:00
parent 0c108f6054 763d06edb7
commit c987abf9f5
28 changed files with 777 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server.cpp
+2 -1
View File
@@ -9,6 +9,7 @@
#include "sampling.h"
#include "speculative.h"
#include "mtmd.h"
#include "mtmd-helper.h"
// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
@@ -4187,7 +4188,7 @@ int main(int argc, char ** argv) {
throw std::runtime_error("This server does not support multimodal");
}
for (auto & file : files) {
mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(file.data(), file.size()));
mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(ctx_server.mctx, file.data(), file.size()));
if (!bmp.ptr) {
throw std::runtime_error("Failed to load image or audio file");
}
tools/server/utils.hpp
+11 -4
View File
@@ -6,6 +6,7 @@
#include "arg.h" // common_remote_get_content
#include "base64.hpp"
#include "mtmd.h"
#include "mtmd-helper.h"
// increase max payload length to allow use of larger context size
#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
@@ -264,13 +265,19 @@ static size_t validate_utf8(const std::string& text) {
static llama_tokens format_rerank(const struct llama_vocab * vocab, const llama_tokens & query, const llama_tokens & doc) {
llama_tokens result;
// Get EOS token - use SEP token as fallback if EOS is not available
llama_token eos_token = llama_vocab_eos(vocab);
if (eos_token == LLAMA_TOKEN_NULL) {
eos_token = llama_vocab_sep(vocab);
}
result.reserve(doc.size() + query.size() + 4);
result.push_back(llama_vocab_bos(vocab));
result.insert(result.end(), query.begin(), query.end());
result.push_back(llama_vocab_eos(vocab));
result.push_back(eos_token);
result.push_back(llama_vocab_sep(vocab));
result.insert(result.end(), doc.begin(), doc.end());
result.push_back(llama_vocab_eos(vocab));
result.push_back(eos_token);
return result;
}
@@ -573,7 +580,7 @@ struct oaicompat_parser_options {
// used by /chat/completions endpoint
static json oaicompat_chat_params_parse(
const json & body, /* openai api json semantics */
json & body, /* openai api json semantics */
const oaicompat_parser_options & opt,
std::vector<raw_buffer> & out_files)
{
@@ -624,7 +631,7 @@ static json oaicompat_chat_params_parse(
if (!body.contains("messages")) {
throw std::runtime_error("'messages' is required");
}
json messages = body.at("messages");
json & messages = body.at("messages");
if (!messages.is_array()) {
throw std::runtime_error("Expected 'messages' to be an array");
}