happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
gemma.cpp/gemma
History
Jan Wassenberg 035273c184 tune pool kSpin mode in threading_context 
Previously, this happened concurrently with the matmul autotune, which could lead to incorrect outcomes.

threading: de-singleton Pinning (no longer stores affinity); pass PoolWorkerMapping; fix Pool dtor order
Also enable SPR target (Zen4 is AMD-only),
update Highway version for renamed Thread()->GlobalIdx().
PiperOrigin-RevId: 816223017
 		2025-10-07 08:36:26 -07:00
..
bindings Replace mt19937 with new generator to enable parallel sampling 2025-09-04 23:49:10 -07:00
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
activations.h Fix gemma_batch_bench for flash attention 2025-09-10 05:32:34 -07:00
api_client.cc feature: add API server and client with Google protocol 2025-08-21 11:32:48 +09:00
api_server.cc tune pool kSpin mode in threading_context 2025-10-07 08:36:26 -07:00
attention.cc tune pool kSpin mode in threading_context 2025-10-07 08:36:26 -07:00
attention.h Added flash attention, with both a single-q function, and a register-tiled function. 2025-09-09 08:05:26 -07:00
configs.cc Remove Griffin support 2025-09-05 02:35:40 -07:00
configs.h 1.03x speedup: fused FFN 2025-09-15 10:26:37 -07:00
configs_test.cc Minor: rename compression/shared -> types.h 2025-05-13 06:53:21 -07:00
flash_attention.cc Reduced parallelism for TransposeQ, making each thread read and write within its own cache lines 2025-10-02 08:15:16 -07:00
flash_attention.h Added a smaller tile size to flash attention for smaller batch sizes 2025-09-30 05:49:20 -07:00
flash_attention_test.cc Added a smaller tile size to flash attention for smaller batch sizes 2025-09-30 05:49:20 -07:00
gemma-inl.h tune pool kSpin mode in threading_context 2025-10-07 08:36:26 -07:00
gemma.cc tune pool kSpin mode in threading_context 2025-10-07 08:36:26 -07:00
gemma.h (1) Added QueryResultAndMetrics and BatchQueryModelWithMetrics to also return TimingInfo besides query results. 2025-09-23 17:02:29 -07:00
gemma_args.h Matmul refactoring towards fusion 2025-09-09 07:13:38 -07:00
kv_cache.cc Remove Griffin support 2025-09-05 02:35:40 -07:00
kv_cache.h Remove Griffin support 2025-09-05 02:35:40 -07:00
model_store.cc Remove Griffin support 2025-09-05 02:35:40 -07:00
model_store.h Write SBS progressively. 2025-07-31 06:05:38 -07:00
run.cc Replace mt19937 with new generator to enable parallel sampling 2025-09-04 23:49:10 -07:00
tensor_info.cc Remove Griffin support 2025-09-05 02:35:40 -07:00
tensor_info.h Remove Griffin support 2025-09-05 02:35:40 -07:00
tensor_info_test.cc Minor: ModelWeightsPtrs -> WeightsPtrs 2025-07-11 06:11:51 -07:00
tokenizer.cc (Resubmit) Prepare profiler annotations for new API 2025-08-13 01:38:24 -07:00
tokenizer.h 6x large-batch, short-prompt prefill speedup 2025-06-10 09:56:20 -07:00
vit.cc tune pool kSpin mode in threading_context 2025-10-07 08:36:26 -07:00
vit.h Minor: ModelWeightsPtrs -> WeightsPtrs 2025-07-11 06:11:51 -07:00
weights.cc Utilize multiple cores to read weight batches. 2025-09-26 11:28:33 -07:00
weights.h Remove Griffin support 2025-09-05 02:35:40 -07:00