CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

clip : use FA (#16837)

Browse Source 
* clip : use FA

* cont : add warning about unsupported ops

* implement "auto" mode for clip flash attn

* clip : print more detailed op support info during warmup

* cont : remove obsolete comment [no ci]

* improve debugging message

* trailing space

* metal : remove stray return

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Georgi Gerganov
2025-11-02 22:21:48 +02:00
committed by GitHub
parent cd5e3b5754
commit 2f966b8ed8
9 changed files with 194 additions and 43 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());