mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-02 02:51:17 +02:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # docs/build-s390x.md # docs/ops.md # docs/ops/zDNN.csv # ggml/include/ggml-zdnn.h # ggml/src/ggml-sycl/binbcast.cpp # ggml/src/ggml-sycl/concat.cpp # ggml/src/ggml-sycl/conv.cpp # ggml/src/ggml-sycl/convert.cpp # ggml/src/ggml-sycl/cpy.cpp # ggml/src/ggml-sycl/dmmv.cpp # ggml/src/ggml-sycl/dpct/helper.hpp # ggml/src/ggml-sycl/element_wise.cpp # ggml/src/ggml-sycl/getrows.cpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-sycl/gla.cpp # ggml/src/ggml-sycl/im2col.cpp # ggml/src/ggml-sycl/mmq.cpp # ggml/src/ggml-sycl/mmvq.cpp # ggml/src/ggml-sycl/norm.cpp # ggml/src/ggml-sycl/rope.cpp # ggml/src/ggml-sycl/set_rows.cpp # ggml/src/ggml-sycl/softmax.cpp # ggml/src/ggml-sycl/tsembd.cpp # ggml/src/ggml-sycl/wkv.cpp # ggml/src/ggml-zdnn/ggml-zdnn-impl.h # ggml/src/ggml-zdnn/ggml-zdnn.cpp # tools/llama-bench/llama-bench.cpp
This commit is contained in:
@@ -181,7 +181,7 @@ llama_context::llama_context(
|
||||
// graph outputs buffer
|
||||
{
|
||||
// resized during inference when a batch uses more outputs
|
||||
if ((uint32_t) output_reserve(params.n_seq_max) < params.n_seq_max) {
|
||||
if (output_reserve(params.n_seq_max) < params.n_seq_max) {
|
||||
throw std::runtime_error("failed to reserve initial output buffer");
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user