removed llama from common

2023-11-30 06:59:10 -05:00 · 2023-11-30 06:59:10 -05:00 · cd5e1901d9
commit cd5e1901d9
parent b0024a6be2
28 changed files with 56 additions and 29 deletions
--- a/6
+++ b/6
@ -513,7 +513,7 @@ override CFLAGS        := $(MK_CPPFLAGS) $(CPPFLAGS) $(MK_CFLAGS) $(CFLAGS)
 override CXXFLAGS      := $(MK_CPPFLAGS) $(CPPFLAGS) $(MK_CXXFLAGS) $(CXXFLAGS)
 override CUDA_CXXFLAGS := $(MK_CUDA_CXXFLAGS) $(CUDA_CXXFLAGS)
 override HOST_CXXFLAGS := $(MK_HOST_CXXFLAGS) $(HOST_CXXFLAGS)
-override LDFLAGS       := $(MK_LDFLAGS) $(LDFLAGS)
+override LDFLAGS       := $(MK_LDFLAGS) $(LDFLAGS) -ldynet

 # save CXXFLAGS before we add host-only options
 NVCCFLAGS := $(NVCCFLAGS) $(CXXFLAGS) $(CUDA_CXXFLAGS) -Wno-pedantic -Xcompiler "$(HOST_CXXFLAGS)"
@ -587,7 +587,7 @@ clean:
 #

 main: examples/main/main.cpp                                  ggml.o llama.o $(COMMON_DEPS) console.o grammar-parser.o $(OBJS) 
-	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS) -ldynet
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS) 
 	@echo
 	@echo '====  Run ./main -h for help.  ===='
 	@echo
@ -740,3 +740,5 @@ tests/test-tokenizer-1-llama: tests/test-tokenizer-1-llama.cpp ggml.o llama.o $(

 tests/test-c.o: tests/test-c.cpp llama.h
 	$(CXX) $(CXXFLAGS) -c $(filter-out %.h,$^) -o $@
+testclang:
+	clang 	-std=c++20 libdynet.cpp
--- a/binding.py
+++ b/binding.py
@ -14,7 +14,8 @@ llvmLibPath = "/usr/lib/llvm-15/lib/"
 cxxClientRoot = "/home/mdupont/experiments/llama.cpp/"

 fileList = [
-    "ggml.cpp",
+    "libdynet.cpp",
+#    "ggml.cpp",
 #    "llama.cpp",
 #    "examples/server/server.cpp",
 ]
@ -34,7 +35,9 @@ def list_headers_in_dir(path):
    # list all the files in the folder
    files = os.listdir(path)
    # only include .hxx files
-    files = list(filter(lambda x: x.endswith('.hxx'), files))
+    files = list(filter(lambda x:
+                        x.endswith('.hpp') or x.endswith('.h')
+                        , files))
    # add the folder path back on
    files = list(map(lambda x: path + x, files))
    return files
--- a/common/common.cpp
+++ b/common/common.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <algorithm>
 #include <cassert>
--- a/common/common.h
+++ b/common/common.h
@ -2,7 +2,7 @@

 #pragma once

-#include "llama.h"
+//#include "llama.h"

 #include "sampling.h"

--- a/common/grammar-parser.cpp
+++ b/common/grammar-parser.cpp
@ -1,3 +1,4 @@
+#include "llama.h"
 #include "grammar-parser.h"
 #include <cstdint>
 #include <cwchar>
--- a/common/grammar-parser.h
+++ b/common/grammar-parser.h
@ -10,7 +10,7 @@
 // space ::= [ \t\n]*

 #pragma once
-#include "llama.h"
+//#include "llama.h"
 #include <vector>
 #include <map>
 #include <cstdint>
--- a/common/sampling.cpp
+++ b/common/sampling.cpp
@ -1,3 +1,4 @@
+#include "llama.h"
 #include "sampling.h"

 struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_params & params) {
--- a/common/sampling.h
+++ b/common/sampling.h
@ -1,6 +1,6 @@
 #pragma once

-#include "llama.h"
+//#include "llama.h"

 #include "grammar-parser.h"

--- a/examples/batched-bench/batched-bench.cpp
+++ b/examples/batched-bench/batched-bench.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <algorithm>
 #include <cmath>
--- a/examples/batched/batched.cpp
+++ b/examples/batched/batched.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <algorithm>
 #include <cmath>
--- a/examples/beam-search/beam-search.cpp
+++ b/examples/beam-search/beam-search.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cassert>
 #include <cinttypes>
--- a/examples/benchmark/benchmark-matmult.cpp
+++ b/examples/benchmark/benchmark-matmult.cpp
@ -1,3 +1,4 @@
+#include "llama.h"
 #include "common.h"
 #include "ggml.h"

--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <ctime>

--- a/examples/export-lora/export-lora.cpp
+++ b/examples/export-lora/export-lora.cpp
@ -1,4 +1,4 @@
-
+#include "llama.h"
 #include "common.h"
 #include "ggml.h"
 #include "ggml-alloc.h"
--- a/examples/infill/infill.cpp
+++ b/examples/infill/infill.cpp
@ -1,7 +1,8 @@
+#include "llama.h"
 #include "common.h"

 #include "console.h"
-#include "llama.h"
+
 #include "grammar-parser.h"

 #include <cassert>
--- a/examples/llava/llava-cli.cpp
+++ b/examples/llava/llava-cli.cpp
@ -1,8 +1,10 @@
 #include "ggml.h"
+#include "llama.h"
+#include "llava.h"
 #include "common.h"
 #include "clip.h"
-#include "llava.h"
-#include "llama.h"
+
+

 #include "base64.hpp"

--- a/examples/llava/llava.cpp
+++ b/examples/llava/llava.cpp
@ -1,6 +1,7 @@
 #include "clip.h"
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+
 #include "llava.h"

 #include <cstdio>
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@ -1,7 +1,8 @@
+#include "llama.h"
 #include "common.h"

 #include "console.h"
-#include "llama.h"
+

 #include <cassert>
 #include <cinttypes>
--- a/examples/parallel/parallel.cpp
+++ b/examples/parallel/parallel.cpp
@ -1,8 +1,8 @@
 // A basic application simulating a server with multiple clients.
 // The clients submit requests to the server and they are processed in parallel.
-
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cmath>
 #include <cstdio>
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cmath>
 #include <cstdio>
--- a/examples/quantize-stats/quantize-stats.cpp
+++ b/examples/quantize-stats/quantize-stats.cpp
@ -1,7 +1,8 @@
 #define LLAMA_API_INTERNAL
+#include "llama.h"
 #include "common.h"
 #include "ggml.h"
-#include "llama.h"
+

 #include <algorithm>
 #include <cassert>
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cstdio>
 #include <cstring>
--- a/examples/save-load-state/save-load-state.cpp
+++ b/examples/save-load-state/save-load-state.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <vector>
 #include <cstdio>
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+
 #include "grammar-parser.h"

 #include "../llava/clip.h"
--- a/examples/simple/simple.cpp
+++ b/examples/simple/simple.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cmath>
 #include <cstdio>
--- a/examples/speculative/speculative.cpp
+++ b/examples/speculative/speculative.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cmath>
 #include <cstdio>
--- a/examples/tokenize/tokenize.cpp
+++ b/examples/tokenize/tokenize.cpp
@ -1,5 +1,6 @@
-#include "common.h"
 #include "llama.h"
+#include "common.h"
+

 #include <cmath>
 #include <cstdio>
--- a/examples/train-text-from-scratch/train-text-from-scratch.cpp
+++ b/examples/train-text-from-scratch/train-text-from-scratch.cpp
@ -1,8 +1,9 @@
 #include "ggml.h"
 #include "ggml-alloc.h"
+#include "llama.h"
 #include "common.h"
 #include "train.h"
-#include "llama.h"
+
 #include <unordered_map>
 #include <vector>
 #include <cassert>