vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/full.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-intel.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cli.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	requirements.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-07-19 14:23:33 +08:00
commit 24b9616344
61 changed files with 12994 additions and 936 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -1183,7 +1183,7 @@ struct server_context {
bool process_token(completion_token_output & result, server_slot & slot) {
// remember which tokens were sampled - used for repetition penalties during sampling
const std::string token_str = llama_token_to_piece(ctx, result.tok, false);
const std::string token_str = llama_token_to_piece(ctx, result.tok, params.special);
slot.sampled = result.tok;
// search stop word and delete it