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

Introduce C-style API (#370)

Browse source 
* Major refactoring - introduce C-style API

* Clean up

* Add <cassert>

* Add <iterator>

* Add <algorithm> ....

* Fix timing reporting and accumulation

* Measure eval time only for single-token calls

* Change llama_tokenize return meaning
This commit is contained in:
Georgi Gerganov 2023-03-22 07:32:36 +02:00 • committed by GitHub
parent da0e9fe90c
commit f5a77a629b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
14 changed files with 1954 additions and 1752 deletions
Download patch file Download diff file Expand all files Collapse all files

11
Makefile
View file

@ -220,18 +220,21 @@ default: main quantize
ggml.o: ggml.c ggml.h
$(CC) $(CFLAGS) -c ggml.c -o ggml.o
llama.o: llama.cpp llama.h
$(CXX) $(CXXFLAGS) -c llama.cpp -o llama.o
utils.o: utils.cpp utils.h
$(CXX) $(CXXFLAGS) -c utils.cpp -o utils.o
clean:
rm -f *.o main quantize
main: main.cpp ggml.o utils.o
$(CXX) $(CXXFLAGS) main.cpp ggml.o utils.o -o main $(LDFLAGS)
main: main.cpp ggml.o llama.o utils.o
$(CXX) $(CXXFLAGS) main.cpp ggml.o llama.o utils.o -o main $(LDFLAGS)
@echo "\x1b[36mrun ./main -h for help\x1b[0m"
quantize: quantize.cpp ggml.o utils.o
$(CXX) $(CXXFLAGS) quantize.cpp ggml.o utils.o -o quantize $(LDFLAGS)
quantize: quantize.cpp ggml.o llama.o utils.o
$(CXX) $(CXXFLAGS) quantize.cpp ggml.o llama.o utils.o -o quantize $(LDFLAGS)
#
# Tests