make : add speculative example (#3003)

diff --git a/.gitignore b/.gitignore
index f9244fadccb3d9565bf5dff8e534071ea5e34faa..e4157e804f5f3b2dddcb7b32bd8888f6d65fb890 100644 (file)
--- a/.gitignore
+++ b/.gitignore
@@ -52,6 +52,7 @@ models-mnt
 /baby-llama
 /beam-search
 /save-load-state
+/speculative
 build-info.h
 arm_neon.h
 compile_commands.json

diff --git a/Makefile b/Makefile
index c042bf0e5f72f5604fd18a8088eeb7de8703967a..9ff2f9e953146f9cc4495f42754ddf740d19dbc1 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,5 @@
 # Define the default target now so that it is always the first target
-BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch convert-llama2c-to-ggml simple save-load-state server embd-input-test gguf llama-bench baby-llama beam-search tests/test-c.o
+BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch convert-llama2c-to-ggml simple save-load-state server embd-input-test gguf llama-bench baby-llama beam-search speculative tests/test-c.o
 
 # Binaries only useful for tests
 TEST_TARGETS = tests/test-llama-grammar tests/test-grammar-parser tests/test-double-float tests/test-grad0 tests/test-opt tests/test-quantize-fns tests/test-quantize-perf tests/test-sampling tests/test-tokenizer-0-llama tests/test-tokenizer-0-falcon tests/test-tokenizer-1
@@ -477,6 +477,9 @@ baby-llama: examples/baby-llama/baby-llama.cpp ggml.o llama.o common.o $(OBJS)
 beam-search: examples/beam-search/beam-search.cpp build-info.h ggml.o llama.o common.o $(OBJS)
        $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
+speculative: examples/speculative/speculative.cpp build-info.h ggml.o llama.o common.o $(OBJS)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+
 ifneq '' '$(or $(filter clean,$(MAKECMDGOALS)),$(LLAMA_METAL))'
 BUILD_TARGETS += metal
 endif