vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 16:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "Revert "llama : disable graph reuse with pipeline parallelism (#20463)""

Browse source 
This reverts commit 8043f35b22.
This commit is contained in:
Concedo 2026-03-25 22:25:20 +08:00
parent b81103d6ba
commit c6213e9be6
3 changed files with 17 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama-context.cpp
View file

@ -350,6 +350,14 @@ llama_context::llama_context(
if (cparams.pipeline_parallel) {
LLAMA_LOG_INFO("%s: pipeline parallelism enabled\n", __func__);
if (!graph_reuse_disable) {
// TODO: figure out a way to make graph reuse work with pipeline parallelism
// ref: https://github.com/ggml-org/llama.cpp/pull/20463
LLAMA_LOG_WARN("%s: graph reuse is currently not compatible with pipeline parallelism - disabling\n", __func__);
graph_reuse_disable = true;
}
}
sched_reserve();