mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 14:52:20 +00:00
9e2fdf57c0
* Removing IPEX_AVAIL. Chose to unify CPU and XPU under `ipex`. Most code is exactly similar except for a very few spots. The biggest number of spots is the kv-cache layout and the flash_xxx.py files. Since those files should be removed soon and factored away, we should not need them. * Forgot a few places. * Unrelated change. * Fixing HF_TOKEN. * HF_TOKEN
14 lines
606 B
Python
14 lines
606 B
Python
from text_generation_server.utils.import_utils import SYSTEM
|
|
import os
|
|
|
|
if os.getenv("USE_FLASH_ATTENTION", "").lower() == "false":
|
|
raise ImportError("`USE_FLASH_ATTENTION` is false.")
|
|
if SYSTEM == "cuda":
|
|
from .cuda import attention, paged_attention, reshape_and_cache, SUPPORTS_WINDOWING
|
|
elif SYSTEM == "rocm":
|
|
from .rocm import attention, paged_attention, reshape_and_cache, SUPPORTS_WINDOWING
|
|
elif SYSTEM == "ipex":
|
|
from .ipex import attention, paged_attention, reshape_and_cache, SUPPORTS_WINDOWING
|
|
else:
|
|
raise ImportError(f"System {SYSTEM} doesn't support flash/paged attention")
|