| .. |
|
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
|
Introduce attention implementation configurability.
|
2025-11-06 08:43:41 -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
|
Minor: ParallelismStrategy->Parallelism
|
2025-11-06 06:56:10 -08:00 |
|
attention.h
|
Also update attention.h to type-erased query_norm_scale
|
2025-10-28 06:48:33 -07:00 |
|
configs.cc
|
Add config flag for global timescale & rely on config to deduce wrapping
|
2025-10-24 06:54:56 -07:00 |
|
configs.h
|
Introduce attention implementation configurability.
|
2025-11-06 08:43:41 -08:00 |
|
configs_test.cc
|
Minor: rename compression/shared -> types.h
|
2025-05-13 06:53:21 -07:00 |
|
flash_attention.cc
|
Minor: ParallelismStrategy->Parallelism
|
2025-11-06 06:56:10 -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
|
Introduce attention implementation configurability.
|
2025-11-06 08:43:41 -08:00 |
|
flash_structs.h
|
Added access to flash attention internals to TileFlashAttention4
|
2025-10-30 06:50:05 -07:00 |
|
gemma-inl.h
|
Minor: ParallelismStrategy->Parallelism
|
2025-11-06 06:56:10 -08:00 |
|
gemma.cc
|
Refactor for continous batching. This cl does not change the current behavior of the code. It only extract two functions that will later be called for adding continuous batching.
|
2025-11-06 14:20:17 -08:00 |
|
gemma.h
|
[Gemma.cpp] Allows non-owned arguments for attention methods.
|
2025-10-27 10:43:25 -07:00 |
|
gemma_args.h
|
Introduce attention implementation configurability.
|
2025-11-06 08:43:41 -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
|
[Gemma.cpp] Allows non-owned arguments for attention methods.
|
2025-10-27 10:43:25 -07:00 |
|
model_store.cc
|
Add 8-bit integer quantization (I8Stream) to Gemma.cpp.
|
2025-10-15 09:25:20 -07:00 |
|
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
|
Major cleanup of profiler zones, add Caller annotation for all pool.Run
|
2025-10-23 01:54:24 -07:00 |
|
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 |
f8131339a7