File tree Expand file tree Collapse file tree 1 file changed +16
-0
lines changed Expand file tree Collapse file tree 1 file changed +16
-0
lines changed Original file line number Diff line number Diff line change @@ -3538,6 +3538,22 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
3538
3538
}
3539
3539
).set_examples ({LLAMA_EXAMPLE_SERVER}));
3540
3540
3541
+ add_opt (common_arg (
3542
+ {" --fim-qwen-30b-default" },
3543
+ string_format (" use default Qwen 3 Coder 30B A3B Instruct (note: can download weights from the internet)" ),
3544
+ [](common_params & params) {
3545
+ params.model .hf_repo = " ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF" ;
3546
+ params.model .hf_file = " qwen3-coder-30b-a3b-instruct-q8_0.gguf" ;
3547
+ params.port = 8012 ;
3548
+ params.n_gpu_layers = 99 ;
3549
+ params.flash_attn = true ;
3550
+ params.n_ubatch = 1024 ;
3551
+ params.n_batch = 1024 ;
3552
+ params.n_ctx = 0 ;
3553
+ params.n_cache_reuse = 256 ;
3554
+ }
3555
+ ).set_examples ({LLAMA_EXAMPLE_SERVER}));
3556
+
3541
3557
add_opt (common_arg (
3542
3558
{ " --diffusion-steps" }, " N" ,
3543
3559
string_format (" number of diffusion steps (default: %d)" , params.diffusion .steps ),
You can’t perform that action at this time.
0 commit comments