vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 02:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-11-14 21:40:52 +08:00
commit df080b074d
41 changed files with 132106 additions and 130341 deletions
Download patch file Download diff file Expand all files Collapse all files

4
include/llama.h
View file

@ -799,7 +799,7 @@ extern "C" {
// Processes a batch of tokens with the ecoder part of the encoder-decoder model.
// Stores the encoder output internally for later use by the decoder cross-attention layers.
// 0 - success
// < 0 - error
// < 0 - error. the KV cache state is restored to the state before this call
LLAMA_API int32_t llama_encode(
struct llama_context * ctx,
struct llama_batch batch);
@ -807,7 +807,7 @@ extern "C" {
// Positive return values does not mean a fatal error, but rather a warning.
// 0 - success
// 1 - could not find a KV slot for the batch (try reducing the size of the batch or increase the context)
// < 0 - error
// < 0 - error. the KV cache state is restored to the state before this call
LLAMA_API int32_t llama_decode(
struct llama_context * ctx,
struct llama_batch batch);