CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : refactored the task processing logic (#5065)

Browse Source 
* server: add llama_server_queue struct

* server: add llama_server_response_event

* server: add comments

* server: move all mutexes away from server.cpp

* server: correct multitask response

* server: only add back deferred tasks when one slot is available

* server: fix a race condition cause by "request_completion"
This commit is contained in:
Xuan Son Nguyen
2024-01-26 13:42:20 +01:00
committed by GitHub
parent 413e7b0559
commit 48c857aa10
5 changed files with 876 additions and 692 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -619,7 +619,7 @@ embedding: examples/embedding/embedding.cpp ggml.o llama.o $(C
save-load-state: examples/save-load-state/save-load-state.cpp 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 examples/llava/clip.cpp examples/llava/clip.h common/stb_image.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
server: examples/server/server.cpp examples/server/oai.hpp examples/server/utils.hpp 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 ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS) $(LWINSOCK2) -Wno-cast-qual
gguf: examples/gguf/gguf.cpp ggml.o $(OBJS)