text-generation-inference/backends/gaudi/server/text_generation_server/layers/attention
baptiste 7cdbd694b3 fix(gaudi): refactor server and implement requested changes
wip(gaudi): fix typos

wip(gaudi): refactor version numbers for pytorch and habana software to make it more flexible

wip(gaudi): debugging the refactored server

wip(gaudi): delete useless files

fix(gaudi): server working after refactoring

fix(gaudi): refactor and implement requested changes
2025-02-27 12:59:28 +00:00
..
__init__.py fix(gaudi): refactor server and implement requested changes 2025-02-27 12:59:28 +00:00
common.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00
cuda.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00
flash_attn_triton.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00
flashinfer.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00
ipex.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00
rocm.py wip(gaudi): import server and dockerfile from tgi-gaudi fork 2025-02-25 12:08:42 +00:00