root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix make bui;d errors

Browse Source
This commit is contained in:
FSSRepo 2023-10-17 17:18:56 -04:00
parent ed0c11cb83
commit d2b1fac6c7
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -605,7 +605,7 @@ embedding: examples/embedding/embedding.cpp build-info.h ggml.
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp examples/server/index.html.hpp examples/server/index.js.hpp examples/server/completion.js.hpp build-info.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp examples/server/index.html.hpp examples/server/index.js.hpp examples/server/completion.js.hpp examples/llava/clip.cpp examples/llava/clip.h common/stb_image.h build-info.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS) $(LWINSOCK2)
$(LIB_PRE)embdinput$(DSO_EXT): examples/embd-input/embd-input.h examples/embd-input/embd-input-lib.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)

4
examples/server/server.cpp
View File

@ -922,8 +922,8 @@ struct llama_server_context
const int n_left = slot.n_past - params.n_keep - 1;
const int n_discard = n_left / 2;
llama_kv_cache_seq_rm (ctx, 0, params.n_keep + 1 , params.n_keep + n_discard + 1);
llama_kv_cache_seq_shift(ctx, 0, params.n_keep + 1 + n_discard, slot.n_past, -n_discard);
llama_kv_cache_seq_rm (ctx, slot.id, params.n_keep + 1 , params.n_keep + n_discard + 1);
llama_kv_cache_seq_shift(ctx, slot.id, params.n_keep + 1 + n_discard, slot.n_past, -n_discard);
for (size_t i = params.n_keep + 1 + n_discard; i < slot.cache_tokens.size(); i++)
{