gemma.cpp/evals
Jan Wassenberg f74d496879 Threading/infra improvements.
* Add Parallelize*Range helpers and partitioning helpers
* Refactor Pinning class, store original affinity (required to construct another NestedPools after pinning happened)

Compress:
* prevent Compress printing stats in tests
* zero-pad tensors

Matmul:
* add matmul_unit_test (TODO) and bench_matmul
* matmul_test: change norm to row vectors (that is what is added) and include bf16 rounding error
* Prepare for L2/L3 retrieval
PiperOrigin-RevId: 700603811
2024-11-27 01:12:00 -08:00
..
benchmark.cc Eliminated TConfig. 2024-10-17 05:04:22 -07:00
benchmark_helper.cc Threading/infra improvements. 2024-11-27 01:12:00 -08:00
benchmark_helper.h Use NestedPools, add NUMA infra 2024-10-18 08:11:18 -07:00
benchmarks.cc Introduce QueryResult in GemmaEnv and add a shortcut for WrapAndTokenize. 2024-10-14 04:45:21 -07:00
cross_entropy.cc Make top_k a runtime argument (instead of a model argument). 2024-11-13 09:48:59 -08:00
cross_entropy.h Introduce QueryResult in GemmaEnv and add a shortcut for WrapAndTokenize. 2024-10-14 04:45:21 -07:00
debug_prompt.cc Introduce QueryResult in GemmaEnv and add a shortcut for WrapAndTokenize. 2024-10-14 04:45:21 -07:00
gemma_batch_bench.cc Add a simple benchmark for batching. 2024-11-21 10:59:49 -08:00
gemma_test.cc Make top_k a runtime argument (instead of a model argument). 2024-11-13 09:48:59 -08:00
prompts.h Benchmark gemma.cpp with different length inputs. 2024-10-10 15:59:26 -07:00
run_mmlu.cc Make top_k a runtime argument (instead of a model argument). 2024-11-13 09:48:59 -08:00