The gemma.cpp Authors da7507e6f0 Add prompt batching to Gemma.cpp. ... This CL adds a new function to Gemma that allows for batching of multiple prompts. The function takes a vector of prompts and returns a vector of responses. The prompts are processed in parallel, and the responses are returned in the same order as the prompts. PiperOrigin-RevId: 648367559		2024-07-01 07:51:31 -07:00
..
evals	Add MMLU eval to github	2024-05-20 10:20:53 -07:00
activations.h	Add Adam optimizer.	2024-06-06 18:41:36 +00:00
benchmark.cc	Major duplicated code reduction in test/benchmarks	2024-06-14 00:16:25 -07:00
benchmark_helper.cc	Add prompt batching to Gemma.cpp.	2024-07-01 07:51:31 -07:00
benchmark_helper.h	Add prompt batching to Gemma.cpp.	2024-07-01 07:51:31 -07:00
benchmarks.cc	Major duplicated code reduction in test/benchmarks	2024-06-14 00:16:25 -07:00
common.cc	Introduce new Gemma 9B and 27B configs	2024-06-27 06:45:24 -07:00
common.h	Introduce new Gemma 9B and 27B configs	2024-06-27 06:45:24 -07:00
compress_weights.cc	Fixing two typos.	2024-06-20 11:33:12 -07:00
configs.h	Introduce new Gemma 9B and 27B configs	2024-06-27 06:45:24 -07:00
cross_entropy.cc	Major duplicated code reduction in test/benchmarks	2024-06-14 00:16:25 -07:00
cross_entropy.h	Support all weight types in a single binary.	2024-06-07 09:04:45 -07:00
gemma.cc	Add prompt batching to Gemma.cpp.	2024-07-01 07:51:31 -07:00
gemma.h	Add prompt batching to Gemma.cpp.	2024-07-01 07:51:31 -07:00
gemma_test.cc	Add prompt batching to Gemma.cpp.	2024-07-01 07:51:31 -07:00
ops.h	Code cleanup	2024-06-20 01:10:24 -07:00
ops_test.cc	Fix DASSERT - TiledBatch requires at least 2 vectors.	2024-06-17 04:29:01 -07:00
run.cc	Fix a clang tidy warning	2024-06-25 09:02:59 -07:00
run_mmlu.cc	Major duplicated code reduction in test/benchmarks	2024-06-14 00:16:25 -07:00
weights.cc	Further simplification to ForEachTensor, thanks I.K.	2024-06-17 07:12:26 -07:00
weights.h	Fix compilation errors in clang	2024-06-21 13:40:40 +08:00
weights_raw.h	Move raw_weights into separate header, used mainly by compress_weights.	2024-06-17 06:17:02 -07:00