| .. |
|
evals
|
Add MMLU eval to github
|
2024-05-20 10:20:53 -07:00 |
|
instantiations
|
Rename Gemma9B and Gemma27B to Gemma2_9B and Gemma2_27B.
|
2024-08-09 02:09:06 -07:00 |
|
activations.h
|
Major MatMul update, 1.9-2.3x speedup on Zen4 via bf16 mul
|
2024-08-16 07:52:20 -07:00 |
|
common.cc
|
Rename Gemma9B and Gemma27B to Gemma2_9B and Gemma2_27B.
|
2024-08-09 02:09:06 -07:00 |
|
common.h
|
Major MatMul update, 1.9-2.3x speedup on Zen4 via bf16 mul
|
2024-08-16 07:52:20 -07:00 |
|
configs.h
|
Major MatMul update, 1.9-2.3x speedup on Zen4 via bf16 mul
|
2024-08-16 07:52:20 -07:00 |
|
gemma-inl.h
|
Fix prefill for batched queries.
|
2024-08-19 08:50:42 -07:00 |
|
gemma.cc
|
Expose underlying model configuration: number of layers, heads, etc.
|
2024-08-16 09:03:24 -07:00 |
|
gemma.h
|
Expose underlying model configuration: number of layers, heads, etc.
|
2024-08-16 09:03:24 -07:00 |
|
kv_cache.cc
|
Major revamp #2 of Prefill: fix token order, parallel for multi-query
|
2024-07-25 03:28:55 -07:00 |
|
kv_cache.h
|
Major revamp #2 of Prefill: fix token order, parallel for multi-query
|
2024-07-25 03:28:55 -07:00 |
|
run.cc
|
Simplify pos handling, auto-increment output arg
|
2024-08-15 09:25:26 -07:00 |
|
tokenizer.cc
|
7x compile time speedup: shard gemma.cc
|
2024-07-03 06:35:04 -07:00 |
|
tokenizer.h
|
7x compile time speedup: shard gemma.cc
|
2024-07-03 06:35:04 -07:00 |
|
weights.cc
|
1.3x prefill, 0.95x decode: matmul replacing last matvec
|
2024-08-12 03:36:01 -07:00 |
|
weights.h
|
Major MatMul update, 1.9-2.3x speedup on Zen4 via bf16 mul
|
2024-08-16 07:52:20 -07:00 |
18e6012872