vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Introduce llama-run (#10291)

Browse source 
It's like simple-chat but it uses smart pointers to avoid manual
memory cleanups. Less memory leaks in the code now. Avoid printing
multiple dots. Split code into smaller functions. Uses no exception
handling.

Signed-off-by: Eric Curtin <ecurtin@redhat.com>
This commit is contained in:
Eric Curtin 2024-11-25 16:56:24 -05:00 • committed by GitHub
parent 50d5cecbda
commit 0cc63754b8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 458 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Makefile
View file

@ -34,6 +34,7 @@ BUILD_TARGETS = \
llama-server \
llama-simple \
llama-simple-chat \
llama-run \
llama-speculative \
llama-tokenize \
llama-vdot \
@ -1167,6 +1168,11 @@ llama-infill: examples/infill/infill.cpp \
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
llama-run: examples/run/run.cpp \
$(OBJ_ALL)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
llama-simple: examples/simple/simple.cpp \
$(OBJ_ALL)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)