| .. |
|
bindings
|
Move MatMulEnv out of Gemma to enable concurrent calls
|
2025-06-23 01:20:09 -07:00 |
|
evals
|
Add MMLU eval to github
|
2024-05-20 10:20:53 -07:00 |
|
activations.h
|
1.1x prefill and decode speedup (attention/activations)
|
2025-06-20 08:59:53 -07:00 |
|
attention.cc
|
1.1x prefill and decode speedup (attention/activations)
|
2025-06-20 08:59:53 -07:00 |
|
attention.h
|
1.1x prefill and decode speedup (attention/activations)
|
2025-06-20 08:59:53 -07:00 |
|
configs.cc
|
Batch inference fixes: set pos during prefill, fix assert
|
2025-06-17 07:09:44 -07:00 |
|
configs.h
|
1.02x batch decode speedup: BF16 KV cache
|
2025-06-17 23:21:59 -07:00 |
|
configs_test.cc
|
Minor: rename compression/shared -> types.h
|
2025-05-13 06:53:21 -07:00 |
|
gemma-inl.h
|
1.1x prefill and decode speedup (attention/activations)
|
2025-06-20 08:59:53 -07:00 |
|
gemma.cc
|
Move MatMulEnv out of Gemma to enable concurrent calls
|
2025-06-23 01:20:09 -07:00 |
|
gemma.h
|
Move MatMulEnv out of Gemma to enable concurrent calls
|
2025-06-23 01:20:09 -07:00 |
|
gemma_args.h
|
Add --prompt_file and testdata for it. Refs #608
|
2025-06-16 23:41:07 -07:00 |
|
griffin.cc
|
Speed up builds by skipping rarely used targets
|
2025-06-17 05:44:20 -07:00 |
|
griffin.h
|
Major refactor: clarify query_idx (global) vs qi. Refs #607
|
2025-06-16 02:42:02 -07:00 |
|
kv_cache.cc
|
MatPtr-ify KV, shared div_seq_len, --seq_len flag
|
2025-06-11 09:49:38 -07:00 |
|
kv_cache.h
|
1.02x batch decode speedup: BF16 KV cache
|
2025-06-17 23:21:59 -07:00 |
|
model_store.cc
|
1.02x batch decode speedup: BF16 KV cache
|
2025-06-17 23:21:59 -07:00 |
|
model_store.h
|
Remove backprop/
|
2025-05-28 07:01:17 -07:00 |
|
run.cc
|
Move MatMulEnv out of Gemma to enable concurrent calls
|
2025-06-23 01:20:09 -07:00 |
|
tensor_info.cc
|
Major refactor to de-templatize gemma-inl and weights
|
2025-06-02 23:01:35 -07:00 |
|
tensor_info.h
|
Minor: rename compression/shared -> types.h
|
2025-05-13 06:53:21 -07:00 |
|
tensor_info_test.cc
|
Major refactor to de-templatize gemma-inl and weights
|
2025-06-02 23:01:35 -07:00 |
|
tokenizer.cc
|
Huge refactor of weight handling and model loading.
|
2025-05-06 04:44:21 -07:00 |
|
tokenizer.h
|
6x large-batch, short-prompt prefill speedup
|
2025-06-10 09:56:20 -07:00 |
|
vit.cc
|
1.1x prefill and decode speedup (attention/activations)
|
2025-06-20 08:59:53 -07:00 |
|
vit.h
|
Further cleanup: separate MatMulEnv arg
|
2025-06-05 20:48:32 -07:00 |
|
weights.cc
|
Update instrumentation for new Highway wall-time profiler
|
2025-06-19 07:46:04 -07:00 |
|
weights.h
|
Split gemma-inl into separate source files
|
2025-06-05 05:36:44 -07:00 |
a04cc287b2