mirror of https://github.com/google/gemma.cpp.git
8532da47f7
use new ThreadingContext2 instead of monostate/init in each frontend Add ThreadingArgs(replaces AppArgs) backprop: use Packed() accessor and MakePacked factory and row-based access to allow for stride compress_weights: remove, moving to py-only exporter instead Move MatPtr to mat.h and revise interface: - Generic MatOwner - rename accessors to Packed* - support stride/row accessors, fix RowPtr stride Add TypeBits(Type) Move GenerateMat to test_util-inl for sharing between matmul test/bench Move internal init to gemma.cc to avoid duplication Rename GemmaEnv model_ to gemma_ for disambiguating vs upcoming ModelStorage Remove --compressed_weights, use --weights instead. tensor_index: add ExtentsFromInfo and TensorIndexLLM/Img Allocator: use normal unique_ptr for AllocBytes so users can call directly threading: use -> because AlignedPtr no longer assumes arrays PiperOrigin-RevId: 745918637 |
||
|---|---|---|
| .. | ||
| benchmark.cc | ||
| benchmark_helper.cc | ||
| benchmark_helper.h | ||
| benchmarks.cc | ||
| cross_entropy.cc | ||
| cross_entropy.h | ||
| debug_prompt.cc | ||
| gemma_batch_bench.cc | ||
| gemma_test.cc | ||
| prompts.h | ||
| run_mmlu.cc | ||