sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 20:44:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

implement "auto" mode for clip flash attn

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-11-01 23:52:40 +01:00
parent 19116a4b38
commit b4955f0ae6
6 changed files with 74 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tools/server/server.cpp
View File

@@ -2456,6 +2456,7 @@ struct server_context {
mparams.print_timings = false;
mparams.n_threads = params_base.cpuparams.n_threads;
mparams.verbosity = params_base.verbosity > 0 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_INFO;
mparams.flash_attn_type = params_base.flash_attn_type;
mctx = mtmd_init_from_file(mmproj_path.c_str(), model, mparams);
if (mctx == nullptr) {
SRV_ERR("failed to load multimodal model, '%s'\n", mmproj_path.c_str());