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