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

lookahead : add example for lookahead decoding (#4207)

Browse source 
* 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>
This commit is contained in:
Georgi Gerganov 2023-11-26 20:33:07 +02:00 • committed by GitHub
parent 22da05536f
commit 922754a8d6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 498 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Makefile
View file

@ -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)