fix compute buffer estimate: tested on cuda

2025-06-22 08:10:57 +00:00
parent 80e5b71b48
commit 45e8b0420c
5 changed files with 68 additions and 30 deletions
@@ -585,7 +585,7 @@ extern "C" {
                  const struct llama_model * model, 
         const struct llama_context_params   cparams, 
                         enum backend_type   backend,
-                                      bool   is_master,
+                                       int   my_rank,
                        struct model_bytes   n_bytes,
                                      bool   offload,
                                      bool   has_gpu_layers);