text-generation-inference/server/text_generation_server/layers/attention
2024-09-25 05:55:39 +00:00
..
__init__.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
common.py Move to FlashDecoding instead of PagedAttention kernel. (#1940) 2024-09-24 03:58:13 +00:00
cuda.py fix: return the out tensor rather then the functions return value (#2361) 2024-09-25 05:55:39 +00:00
flash_attn_triton.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
ipex.py Unify attention output handling (#2343) 2024-09-25 05:55:39 +00:00
rocm.py Unify attention output handling (#2343) 2024-09-25 05:55:39 +00:00