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
Charles Zhao 0e5f4cbf1b Implement Continus Batching. 
(1) A function GenerateTWithContinuousBatching is added to use continuous batching when enabled.

(2) The ContinuousQBatch is added as a subclass of QBatch to manage prefill, insert, used-kv-cache-collection.

(3) Also expanded the unit test to more diverse cases.

PiperOrigin-RevId: 836090261
 		2025-11-23 23:54:02 -08:00
..
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 Added access to softmax attention internals to regular attention 2025-11-21 09:01:01 -08:00
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 Added access to softmax attention internals to regular attention 2025-11-21 09:01:01 -08:00
attention.h Also update attention.h to type-erased query_norm_scale 2025-10-28 06:48:33 -07:00
configs.cc Improves autodetection of Gemma3-1B. 2025-11-17 01:12:50 -08:00
configs.h Improves autodetection of Gemma3-1B. 2025-11-17 01:12:50 -08:00
configs_test.cc Minor: rename compression/shared -> types.h 2025-05-13 06:53:21 -07:00
flash_attention.cc Add some comments. 2025-11-19 01:09:15 -08:00
flash_attention.h Pre-compress query activations to BF16 before FlashAttention. 2025-10-31 09:49:44 -07:00
flash_attention_test.cc Internal change 2025-11-21 01:17:45 -08:00
flash_structs.h Add some comments. 2025-11-19 01:09:15 -08:00
gemma-inl.h Minor: ParallelismStrategy->Parallelism 2025-11-06 06:56:10 -08:00
gemma.cc Implement Continus Batching. 2025-11-23 23:54:02 -08:00
gemma.h Implement Continus Batching. 2025-11-23 23:54:02 -08:00
gemma_args.h Implement Continus Batching. 2025-11-23 23:54:02 -08:00
kv_cache.cc [Gemma.cpp] Allows non-owned arguments for attention methods. 2025-10-27 10:43:25 -07:00
kv_cache.h Implement Continus Batching. 2025-11-23 23:54:02 -08:00
model_store.cc Improves autodetection of Gemma3-1B. 2025-11-17 01:12:50 -08:00
model_store.h Major cleanup of profiler zones, add Caller annotation for all pool.Run 2025-10-23 01:54:24 -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 Add 8-bit integer quantization (I8Stream) to Gemma.cpp. 2025-10-15 09:25:20 -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 Avoid hard-coding kPatchSize. Thanks @Somet2mes for reporting. Fixes #762. 2025-11-07 00:32:31 -08:00
vit.h Minor: ModelWeightsPtrs -> WeightsPtrs 2025-07-11 06:11:51 -07:00
weights.cc Minor: ParallelismStrategy->Parallelism 2025-11-06 06:56:10 -08:00
weights.h Major cleanup of profiler zones, add Caller annotation for all pool.Run 2025-10-23 01:54:24 -07:00