Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
Renable qwen2vl GPU for vulkan https://github.com/ggml-org/llama.cpp/pull/11902

# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.gitignore
#	CONTRIBUTING.md
#	Makefile
#	common/CMakeLists.txt
#	common/arg.cpp
#	common/common.cpp
#	examples/main/main.cpp
#	examples/run/run.cpp
#	examples/server/tests/README.md
#	ggml/src/ggml-cuda/mma.cuh
#	scripts/get_chat_template.py
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
This commit is contained in:
Concedo
2025-02-20 23:17:20 +08:00
parent 41350df81f d04e7163c8
commit 6d7ef10671
42 changed files with 8897 additions and 3215 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+50 -1
View File
@@ -2,6 +2,7 @@
#include "log.h"
#include "sampling.h"
#include "chat.h"
#include "build-info.h"
#include <algorithm>
@@ -2248,7 +2249,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_LOG_VERBOSITY"));
add_opt(common_arg(
{"--log-prefix"},
"Enable prefx in log messages",
"Enable prefix in log messages",
[](common_params &) {
common_log_set_prefix(common_log_main(), true);
}
@@ -2502,5 +2503,53 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--fim-qwen-1.5b-default"},
string_format("use default Qwen 2.5 Coder 1.5B (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF";
params.hf_file = "qwen2.5-coder-1.5b-q8_0.gguf";
params.port = 8012;
params.n_gpu_layers = 99;
params.flash_attn = true;
params.n_ubatch = 1024;
params.n_batch = 1024;
params.n_ctx = 0;
params.n_cache_reuse = 256;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--fim-qwen-3b-default"},
string_format("use default Qwen 2.5 Coder 3B (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF";
params.hf_file = "qwen2.5-coder-3b-q8_0.gguf";
params.port = 8012;
params.n_gpu_layers = 99;
params.flash_attn = true;
params.n_ubatch = 1024;
params.n_batch = 1024;
params.n_ctx = 0;
params.n_cache_reuse = 256;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--fim-qwen-7b-default"},
string_format("use default Qwen 2.5 Coder 7B (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF";
params.hf_file = "qwen2.5-coder-7b-q8_0.gguf";
params.port = 8012;
params.n_gpu_layers = 99;
params.flash_attn = true;
params.n_ubatch = 1024;
params.n_batch = 1024;
params.n_ctx = 0;
params.n_cache_reuse = 256;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
return ctx_arg;
}