Skip to content

LLM inference in C/C++

C++ ggml

context : fix off-by-one comparisons to n_gpu_layers (#24208)

Sigbjørn Skjæret603300b008e0
diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index eff1d8f89f..d0c314199b 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -341,7 +341,7 @@ llama_context::llama_context(
// enabling pipeline parallelism in the scheduler increases memory usage, so it is only done when necessary
bool pipeline_parallel =
model.n_devices() > 1 &&
- model.n_gpu_layers() > model.hparams.n_layer() &&
+ model.n_gpu_layers() > model.hparams.n_layer_all &&
model.split_mode() == LLAMA_SPLIT_MODE_LAYER &&
cparams.offload_kqv &&
!model.has_tensor_overrides();
@@ -2351,7 +2351,7 @@ llm_graph_cb llama_context::graph_get_cb() const {
// norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
// FIXME: fix in ggml_backend_sched
- const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer();
+ const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer_all;
if (ubatch.n_tokens < 32 || full_offload) {
if (il != -1 && strcmp(name, "norm") == 0) {
const auto & dev_layer = model.dev_layer(il);