| .. |
|
test_baichuan.py
|
3f7d5786ba
Pass alibi slopes to flash_attn_with_kvcache during generation
|
11 mesiacov pred |
|
test_bert.py
|
07005806ff
Add BigCode converters (#532)
|
1 rok pred |
|
test_bigcode.py
|
dfe29f5e2b
[Gen] Don't use ft_attention, use flash_attn_with_kvcache instead
|
1 rok pred |
|
test_btlm.py
|
73df3be7d5
Add test for BTLM init
|
11 mesiacov pred |
|
test_falcon.py
|
dfe29f5e2b
[Gen] Don't use ft_attention, use flash_attn_with_kvcache instead
|
1 rok pred |
|
test_gpt.py
|
e0fbaa7016
[Gen] Simplify decode_speculative
|
1 rok pred |
|
test_gpt_generation_parallel.py
|
0705d2718d
[Llama] Fix some tests, add tests for Llama 2 and CodeLlama
|
1 rok pred |
|
test_gpt_neox.py
|
d0032700d1
Add tests for Pythia, GPT-JT, and RedPajama models
|
1 rok pred |
|
test_gpt_parallel.py
|
0e8c46ae08
Run isort and black on test files
|
1 rok pred |
|
test_gptj.py
|
dfe29f5e2b
[Gen] Don't use ft_attention, use flash_attn_with_kvcache instead
|
1 rok pred |
|
test_llama.py
|
0705d2718d
[Llama] Fix some tests, add tests for Llama 2 and CodeLlama
|
1 rok pred |
|
test_opt.py
|
dfe29f5e2b
[Gen] Don't use ft_attention, use flash_attn_with_kvcache instead
|
1 rok pred |
|
test_vit.py
|
0e8c46ae08
Run isort and black on test files
|
1 rok pred |
Tri Dao
73df3be7d5
Add test for BTLM init