tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-02 07:26:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

speculative : add grammar support (#2991)

Browse Source 
* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build
This commit is contained in:
Georgi Gerganov
2023-09-05 08:46:17 +03:00
committed by GitHub
parent 2ba85c8609
commit 921772104b
6 changed files with 126 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -495,7 +495,7 @@ 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)
speculative: examples/speculative/speculative.cpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
ifdef LLAMA_METAL