CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B (#13386)

Browse Source
This commit is contained in:
David Huang
2025-05-11 20:18:39 +08:00
committed by GitHub
parent 3eac209319
commit 7f323a589f
11 changed files with 57 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/mtmd/clip.cpp
View File

@@ -383,7 +383,7 @@ struct clip_ctx {
backend_buft.push_back(ggml_backend_get_default_buffer_type(backend_cpu));
sched.reset(
ggml_backend_sched_new(backend_ptrs.data(), backend_buft.data(), backend_ptrs.size(), 8192, false)
ggml_backend_sched_new(backend_ptrs.data(), backend_buft.data(), backend_ptrs.size(), 8192, false, true)
);
}