vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/main-intel.Dockerfile
#	.devops/main-vulkan.Dockerfile
#	.devops/server-intel.Dockerfile
#	.devops/server-vulkan.Dockerfile
#	.github/workflows/bench.yml
#	.github/workflows/build.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/server.yml
#	.gitignore
#	Makefile
#	README-sycl.md
#	README.md
#	ci/run.sh
#	flake.lock
#	llama.cpp
#	models/ggml-vocab-falcon.gguf
#	models/ggml-vocab-llama-spm.gguf
#	models/ggml-vocab-mpt.gguf
#	models/ggml-vocab-stablelm.gguf
#	models/ggml-vocab-starcoder.gguf
#	requirements.txt
#	scripts/check-requirements.sh
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-tokenizer-0-bpe.py
#	tests/test-tokenizer-0-spm.py
#	tests/test-tokenizer-1-spm.cpp
This commit is contained in:
Concedo 2024-04-30 21:04:17 +08:00
commit 17a24d753c
52 changed files with 4978 additions and 1249 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/main/main.cpp
View file

@ -325,7 +325,7 @@ int main(int argc, char ** argv) {
log_tostr(embd_inp.empty()), n_matching_session_tokens, embd_inp.size(), session_tokens.size(), embd_inp.size());
// if we will use the cache for the full prompt without reaching the end of the cache, force
// reevaluation of the last token token to recalculate the cached logits
// reevaluation of the last token to recalculate the cached logits
if (!embd_inp.empty() && n_matching_session_tokens == embd_inp.size() && session_tokens.size() > embd_inp.size()) {
LOGLN("recalculate the cached logits (do): session_tokens.resize( %zu )", embd_inp.size() - 1);