huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 00:12:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix import

Browse Source
This commit is contained in:
Mohit Sharma 2024-09-27 12:32:17 +00:00
parent 47c81d2924
commit 816d4b67b2
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/layers/attention/__init__.py
View File

@ -11,6 +11,7 @@ if SYSTEM == "cuda":
paged_attention, paged_attention,
reshape_and_cache, reshape_and_cache,
SUPPORTS_WINDOWING, SUPPORTS_WINDOWING,
PREFILL_IN_KV_CACHE,
) )
elif SYSTEM == "rocm": elif SYSTEM == "rocm":
from .rocm import ( from .rocm import (
@ -18,6 +19,7 @@ elif SYSTEM == "rocm":
paged_attention, paged_attention,
reshape_and_cache, reshape_and_cache,
SUPPORTS_WINDOWING, SUPPORTS_WINDOWING,
PREFILL_IN_KV_CACHE,
) )
elif SYSTEM == "ipex": elif SYSTEM == "ipex":
from .ipex import ( from .ipex import (
@ -25,6 +27,7 @@ elif SYSTEM == "ipex":
paged_attention, paged_attention,
reshape_and_cache, reshape_and_cache,
SUPPORTS_WINDOWING, SUPPORTS_WINDOWING,
PREFILL_IN_KV_CACHE,
) )
else: else:
raise ImportError(f"System {SYSTEM} doesn't support flash/paged attention") raise ImportError(f"System {SYSTEM} doesn't support flash/paged attention")
@ -35,5 +38,6 @@ __all__ = [
"paged_attention", "paged_attention",
"reshape_and_cache", "reshape_and_cache",
"SUPPORTS_WINDOWING", "SUPPORTS_WINDOWING",
"PREFILL_IN_KV_CACHE",
"Seqlen", "Seqlen",
] ]