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

llama : add benchmark example (#2626)

Browse source 
* llama : add benchmark example

* add to examples CMakeLists.txt

* fix msvc build

* add missing include

* add Bessel's correction to stdev calculation

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* improve markdown formatting

* add missing include

* print warning is NDEBUG is not defined

* remove n_prompt and n_gen from the matrix, use each value separately instead

* better checks for non-optimized builds

* llama.cpp : fix MEM_REQ_SCRATCH0 reusing the value of n_ctx of the first call

* fix json formatting

* add sql output

* add basic cpu and gpu info (linx/cuda only)

* markdown: also show values that differ from the default

* markdown: add build id

* cleanup

* improve formatting

* formatting

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
slaren 2023-08-18 12:44:58 +02:00 • committed by GitHub
parent eaf98c2649
commit 097e121e2f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 1029 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

7
Makefile
View file

@ -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 server embd-input-test
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch convert-llama2c-to-ggml simple server embd-input-test llama-bench
# 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
@ -345,7 +345,7 @@ libllama.so: llama.o ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
clean:
rm -vf *.o *.so *.dll main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server simple vdot train-text-from-scratch convert-llama2c-to-ggml embd-input-test build-info.h $(TEST_TARGETS)
rm -vf *.o *.so *.dll main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server simple vdot train-text-from-scratch convert-llama2c-to-ggml embd-input-test llama-bench build-info.h $(TEST_TARGETS)
#
# Examples
@ -391,6 +391,9 @@ train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratc
convert-llama2c-to-ggml: examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp build-info.h ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
llama-bench: examples/llama-bench/llama-bench.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
build-info.h: $(wildcard .git/index) scripts/build-info.sh
@sh scripts/build-info.sh > $@.tmp
@if ! cmp -s $@.tmp $@; then \