gemma.cpp/evals
Jan Wassenberg e5c81f64a1 Major refactor: clarify query_idx (global) vs qi. Refs #607
Fix missing pos increment for last prefill and check that in gemma_test.
Thanks to @ufownl for pointing this out.

Change argument lists to QBatch with accessors.
Increase default seq_len to 8k.

PiperOrigin-RevId: 771937385
2025-06-16 02:42:02 -07:00
..
benchmark.cc MatPtr-ify KV, shared div_seq_len, --seq_len flag 2025-06-11 09:49:38 -07:00
benchmark_helper.cc Major refactor: clarify query_idx (global) vs qi. Refs #607 2025-06-16 02:42:02 -07:00
benchmark_helper.h Major refactor: clarify query_idx (global) vs qi. Refs #607 2025-06-16 02:42:02 -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 Huge refactor of weight handling and model loading. 2025-05-06 04:44:21 -07:00
cross_entropy.h Huge refactor of weight handling and model loading. 2025-05-06 04:44:21 -07:00
debug_prompt.cc Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00
gemma_batch_bench.cc 6x large-batch, short-prompt prefill speedup 2025-06-10 09:56:20 -07:00
gemma_test.cc Major refactor: clarify query_idx (global) vs qi. Refs #607 2025-06-16 02:42:02 -07:00
prompts.h Benchmark gemma.cpp with different length inputs. 2024-10-10 15:59:26 -07:00
run_mmlu.cc Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00