lookahead : add example for lookahead decoding (#4207)

* lookahead : init

* lookahead : generate and store n-grams

* lookahead : use loop instead recursion to generate n-grams

* lookahead : initial working implementation

* lookahead : filter repeating n-grams

* lookahead : use deterministic init

* lookahead : add to Makefile

* lookahead : fix a bug in the seq_id of the lookahead tokens

* lookahead : add comments

---------

Co-authored-by: slaren <slarengh@gmail.com>

.gitignore

@@ -47,6 +47,7 @@ models-mnt
 /libllama.so
 /llama-bench
 /llava-cli
+/lookahead
 /main
 /metal
 /perplexity

Makefile

@@ -2,7 +2,7 @@
 BUILD_TARGETS = \
 	main quantize quantize-stats perplexity embedding vdot q8dot train-text-from-scratch convert-llama2c-to-ggml \
 	simple batched batched-bench save-load-state server gguf llama-bench libllava.a llava-cli baby-llama beam-search  \
-	speculative infill tokenize benchmark-matmult parallel finetune export-lora tests/test-c.o
+	speculative infill tokenize benchmark-matmult parallel finetune export-lora lookahead tests/test-c.o
 
 # Binaries only useful for tests
 TEST_TARGETS = \
@@ -657,6 +657,9 @@ speculative: examples/speculative/speculative.cpp ggml.o llama.o $(COMMON_DEPS)
 parallel: examples/parallel/parallel.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
+lookahead: examples/lookahead/lookahead.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+
 ifdef LLAMA_METAL
 metal: examples/metal/metal.cpp ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)

examples/CMakeLists.txt

@@ -32,6 +32,7 @@ else()
     add_subdirectory(save-load-state)
     add_subdirectory(simple)
     add_subdirectory(speculative)
+    add_subdirectory(lookahead)
     add_subdirectory(train-text-from-scratch)
     if (LLAMA_METAL)
         add_subdirectory(metal)

examples/lookahead/CMakeLists.txt

@@ -0,0 +1,5 @@
+set(TARGET lookahead)
+add_executable(${TARGET} lookahead.cpp)
+install(TARGETS ${TARGET} RUNTIME)
+target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)