CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

presets : add qwen3-30B-a3b FIM (#15616)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-08-27 15:48:07 +03:00
committed by GitHub
parent 47373271f9
commit da54f9f1a2
1 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
common/arg.cpp
View File

@@ -3538,6 +3538,22 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--fim-qwen-30b-default"},
string_format("use default Qwen 3 Coder 30B A3B Instruct (note: can download weights from the internet)"),
[](common_params & params) {
params.model.hf_repo = "ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF";
params.model.hf_file = "qwen3-coder-30b-a3b-instruct-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(
{ "--diffusion-steps" }, "N",
string_format("number of diffusion steps (default: %d)", params.diffusion.steps),