Jan Wassenberg 5e433e774a 1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism. ... Limit thread counts to detected. Add max_clusters arg. Update detection logic to check for smt0 - previously we pinned to some siblings. PiperOrigin-RevId: 659755311		2024-08-05 18:50:09 -07:00
..
benchmark.cc	Major revamp #2 of Prefill: fix token order, parallel for multi-query	2024-07-25 03:28:55 -07:00
benchmark_helper.cc	1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism.	2024-08-05 18:50:09 -07:00
benchmark_helper.h	1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism.	2024-08-05 18:50:09 -07:00
benchmarks.cc	Move benchmark_helper to evals/, weights_raw to compression/.	2024-07-08 01:13:23 -07:00
cross_entropy.cc	Cleanup: add ModelInfo struct, remove gcpp::	2024-07-02 07:11:15 -07:00
cross_entropy.h	Declutter gemma/ directory, move binaries to evals/ and util/.	2024-07-01 09:51:04 -07:00
debug_prompt.cc	Extend LayersOutputFunc to take query index and auxillary int	2024-07-30 06:53:56 -07:00
gemma_test.cc	Major revamp #2 of Prefill: fix token order, parallel for multi-query	2024-07-25 03:28:55 -07:00
run_mmlu.cc	Move benchmark_helper to evals/, weights_raw to compression/.	2024-07-08 01:13:23 -07:00