upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

server: add margin for draft model for fit (#23485)

Browse Source
This commit is contained in:
Aman Gupta
2026-05-24 14:43:08 +08:00
committed by GitHub
parent fff63b5108
commit 83eebe9d08
3 changed files with 95 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/fit.cpp
View File

@@ -26,7 +26,7 @@ class common_params_fit_exception : public std::runtime_error {
using std::runtime_error::runtime_error;
};
static std::vector<llama_device_memory_data> common_get_device_memory_data(
std::vector<llama_device_memory_data> common_get_device_memory_data(
const char * path_model,
const llama_model_params * mparams,
const llama_context_params * cparams,